Yotam-Perlitz commited on
Commit
dcfe1ca
1 Parent(s): 13d7cc4

update cahce

Browse files

Signed-off-by: Yotam-Perlitz <y.perlitz@ibm.com>

cache/aggregate_scoress_cache_7b814a45375ad6b75add8b396f69c2cd.csv ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,score
2
+ gpt_4o_2024_05_13,0.9950869236583522
3
+ gpt_4_turbo_2024_04_09,0.9639153609872332
4
+ gpt_4_0125_preview,0.9393939393939394
5
+ claude_3_opus_20240229,0.9220898724004315
6
+ yi_large_preview,0.8845096932053453
7
+ llama3.1_70b_instruct,0.8832459207459207
8
+ qwen2_72b_instruct,0.8719243719243719
9
+ gpt_4_0613,0.8648074952422778
10
+ gemma_2_27b_it,0.8510517260517261
11
+ llama3_70b_instruct,0.849670938694048
12
+ mistral_large,0.8470006184291898
13
+ yi_1.5_34b_chat,0.7714889277389277
14
+ llama3_70b,0.7611156781553201
15
+ claude_3_sonnet_20240229,0.7541101640480523
16
+ mixtral_8x22b_instruct_v0.1,0.7425976800976801
17
+ qwen1.5_110b_chat,0.7320934784170079
18
+ mistral_medium,0.7056277056277057
19
+ phi_3_medium_4k_instruct,0.696301247771836
20
+ qwen1.5_32b_chat,0.6812609659248315
21
+ claude_3_haiku_20240307,0.6757563807253248
22
+ mistral_large_2402,0.6705753184014054
23
+ qwen1.5_72b,0.6692868451728518
24
+ qwen1.5_72b_chat,0.6604933136636727
25
+ command_r_plus,0.6508289415898112
26
+ yi_34b,0.6270777876367939
27
+ phi_3_mini_4k_instruct,0.6218470721621983
28
+ gemma_2_9b_it,0.6216006216006217
29
+ qwen1.5_32b,0.6175551742436105
30
+ llama_2_70b,0.585811187829169
31
+ gpt_3.5_turbo_0125,0.5795841063698206
32
+ yi_34b_chat,0.5793988997113997
33
+ gemini_1.0_pro,0.5205318491032778
34
+ gpt_3.5_turbo_0613,0.5196837944664031
35
+ llama3_8b_instruct,0.5166348882210227
36
+ yi_1.5_9b_chat,0.5150335775335776
37
+ qwen2_7b_instruct,0.4803418803418803
38
+ phi_3_mini_128k_instruct,0.47774531890678346
39
+ mixtral_8x7b_instruct_v0.1,0.47245816635618004
40
+ starling_lm_7b_beta,0.46037960638800973
41
+ qwen1.5_14b_chat,0.45760855624301
42
+ tulu_2_dpo_70b,0.44326821637746006
43
+ llama3.1_8b_instruct,0.4429972804972805
44
+ command_r,0.42476786498525626
45
+ openhermes_2.5_mistral_7b,0.4133219954648526
46
+ mistral_7b_instruct_v0.2,0.38528271156947624
47
+ yi_1.5_6b_chat,0.3616155902920609
48
+ llama_2_70b_chat,0.3429423284465301
49
+ starling_lm_7b_alpha,0.3192125334982478
50
+ llama3_8b,0.3191327255539897
51
+ gemma_1.1_7b_it,0.3093664233370116
52
+ zephyr_7b_beta,0.3012633624878523
53
+ qwen1.5_7b,0.29290520556048505
54
+ gemma_7b,0.29047416067876425
55
+ vicuna_33b_v1.3,0.28480038480038483
56
+ qwen1.5_7b_chat,0.27333417049803604
57
+ llama_2_13b,0.2660179289106947
58
+ mistral_7b_instruct_v0.3,0.21805555555555559
59
+ yi_6b_chat,0.20091647770219198
60
+ yi_6b,0.19687349577512162
61
+ qwen1.5_4b,0.16834733893557421
62
+ vicuna_7b_v1.5,0.14973544973544975
63
+ gemma_7b_it,0.14039115646258504
64
+ qwen1.5_4b_chat,0.14036924293526934
65
+ phi_2,0.1326664119754182
66
+ llama_2_7b_chat,0.11841995751468631
67
+ gemma_1.1_2b_it,0.09431689342403628
68
+ llama_2_7b,0.06859327581964463
69
+ qwen1.5_1.8b_chat,0.06363517629273932
70
+ gemma_2b,0.05727290916366547
71
+ olmo_7b,0.011775543550753635
72
+ qwen1.5_0.5b_chat,0.008163265306122448
cache/aggregate_scoress_cache_bdd8d629730630ed8e73cb56f53f335b.csv ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,score
2
+ gpt_4o_2024_05_13,0.9950869236583522
3
+ gpt_4_turbo_2024_04_09,0.9639153609872332
4
+ gpt_4_0125_preview,0.9393939393939394
5
+ claude_3_opus_20240229,0.9220898724004315
6
+ yi_large_preview,0.8845096932053453
7
+ llama3.1_70b_instruct,0.8832459207459207
8
+ qwen2_72b_instruct,0.8719243719243719
9
+ gpt_4_0613,0.8648074952422778
10
+ gemma_2_27b_it,0.8510517260517261
11
+ llama3_70b_instruct,0.849670938694048
12
+ mistral_large,0.8470006184291898
13
+ yi_1.5_34b_chat,0.7714889277389277
14
+ llama3_70b,0.7611156781553201
15
+ claude_3_sonnet_20240229,0.7541101640480523
16
+ mixtral_8x22b_instruct_v0.1,0.7425976800976801
17
+ qwen1.5_110b_chat,0.7320934784170079
18
+ mistral_medium,0.7056277056277057
19
+ phi_3_medium_4k_instruct,0.696301247771836
20
+ qwen1.5_32b_chat,0.6812609659248315
21
+ claude_3_haiku_20240307,0.6757563807253248
22
+ mistral_large_2402,0.6705753184014054
23
+ qwen1.5_72b,0.6692868451728518
24
+ qwen1.5_72b_chat,0.6604933136636727
25
+ command_r_plus,0.6508289415898112
26
+ yi_34b,0.6270777876367939
27
+ phi_3_mini_4k_instruct,0.6218470721621983
28
+ gemma_2_9b_it,0.6216006216006217
29
+ qwen1.5_32b,0.6175551742436105
30
+ llama_2_70b,0.585811187829169
31
+ gpt_3.5_turbo_0125,0.5795841063698206
32
+ yi_34b_chat,0.5793988997113997
33
+ gemini_1.0_pro,0.5205318491032778
34
+ gpt_3.5_turbo_0613,0.5196837944664031
35
+ llama3_8b_instruct,0.5166348882210227
36
+ yi_1.5_9b_chat,0.5150335775335776
37
+ qwen2_7b_instruct,0.4803418803418803
38
+ phi_3_mini_128k_instruct,0.47774531890678346
39
+ mixtral_8x7b_instruct_v0.1,0.47245816635618004
40
+ starling_lm_7b_beta,0.46037960638800973
41
+ qwen1.5_14b_chat,0.45760855624301
42
+ tulu_2_dpo_70b,0.44326821637746006
43
+ llama3.1_8b_instruct,0.4429972804972805
44
+ command_r,0.42476786498525626
45
+ openhermes_2.5_mistral_7b,0.4133219954648526
46
+ mistral_7b_instruct_v0.2,0.38528271156947624
47
+ yi_1.5_6b_chat,0.3616155902920609
48
+ llama_2_70b_chat,0.3429423284465301
49
+ starling_lm_7b_alpha,0.3192125334982478
50
+ llama3_8b,0.3191327255539897
51
+ gemma_1.1_7b_it,0.3093664233370116
52
+ zephyr_7b_beta,0.3012633624878523
53
+ qwen1.5_7b,0.29290520556048505
54
+ gemma_7b,0.29047416067876425
55
+ vicuna_33b_v1.3,0.28480038480038483
56
+ qwen1.5_7b_chat,0.27333417049803604
57
+ llama_2_13b,0.2660179289106947
58
+ mistral_7b_instruct_v0.3,0.21805555555555559
59
+ yi_6b_chat,0.20091647770219198
60
+ yi_6b,0.19687349577512162
61
+ qwen1.5_4b,0.16834733893557421
62
+ vicuna_7b_v1.5,0.14973544973544975
63
+ gemma_7b_it,0.14039115646258504
64
+ qwen1.5_4b_chat,0.14036924293526934
65
+ phi_2,0.1326664119754182
66
+ llama_2_7b_chat,0.11841995751468631
67
+ gemma_1.1_2b_it,0.09431689342403628
68
+ llama_2_7b,0.06859327581964463
69
+ qwen1.5_1.8b_chat,0.06363517629273932
70
+ gemma_2b,0.05727290916366547
71
+ olmo_7b,0.011775543550753635
72
+ qwen1.5_0.5b_chat,0.008163265306122448
cache/agreements_cache_7b814a45375ad6b75add8b396f69c2cd.csv ADDED
The diff for this file is too large to render. See raw diff
 
cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv DELETED
@@ -1,901 +0,0 @@
1
- scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
2
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
3
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
4
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
5
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
6
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
7
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
8
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
9
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
10
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
11
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
12
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
13
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
14
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
15
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
16
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676
17
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
18
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
19
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
20
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
21
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
22
- planning,biggen_240612,aggregate,holistic,kendall,random,5,0,-0.19999999999999998,0.8166666666666667
23
- planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
24
- planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
25
- planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
26
- planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
27
- planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
28
- planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
29
- planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
30
- planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
31
- planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
32
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
33
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
34
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
35
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
36
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
37
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
38
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
39
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
40
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
41
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
42
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
43
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
44
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
45
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
46
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
47
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
48
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
49
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
50
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
51
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
52
- safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
53
- safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0
54
- safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
55
- safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
56
- safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.7999999999999999,0.08333333333333333
57
- safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
58
- safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
59
- safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
60
- safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
61
- safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0
62
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
63
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
64
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
65
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
66
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
67
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
68
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
69
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
70
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
71
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
72
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0
73
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
74
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
75
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
76
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
77
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
78
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
79
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
80
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
81
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
82
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
83
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
84
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
85
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
86
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
87
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
88
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
89
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
90
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
91
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
92
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
93
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
94
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
95
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
96
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
97
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
98
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
99
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
100
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
101
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
102
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
103
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
104
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
105
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263
106
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
107
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
108
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263
109
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263
110
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425
111
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
112
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
113
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
114
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
115
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
116
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
117
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
118
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
119
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
120
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
121
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
122
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
123
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
124
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
125
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
126
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
127
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
128
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
129
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
130
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
131
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
132
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
133
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
134
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
135
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
136
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
137
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
138
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
139
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
140
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
141
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
142
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
143
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
144
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
145
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
146
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
147
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
148
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
149
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
150
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
151
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
152
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
153
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
154
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
155
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
156
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
157
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
158
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
159
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
160
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
161
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
162
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
163
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
164
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
165
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
166
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
167
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
168
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
169
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
170
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
171
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
172
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
173
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
174
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
175
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
176
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
177
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
178
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
179
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
180
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
181
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
182
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
183
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
184
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
185
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
186
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
187
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
188
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
189
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
190
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
191
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
192
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
193
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
194
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
195
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
196
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
197
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
198
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
199
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
200
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
201
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
202
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
203
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
204
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
205
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.19999999999999998,0.8166666666666667
206
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
207
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
208
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
209
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
210
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
211
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
212
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
213
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
214
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
215
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
216
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
217
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
218
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
219
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
220
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
221
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
222
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
223
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
224
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
225
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
226
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
227
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
228
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
229
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
230
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
231
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
232
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
233
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
234
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
235
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
236
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
237
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
238
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
239
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
240
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
241
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
242
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
243
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
244
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425
245
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
246
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
247
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
248
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
249
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
250
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
251
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
252
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
253
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
254
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
255
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
256
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
257
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
258
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
259
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
260
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
261
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
262
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
263
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
264
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
265
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
266
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
267
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
268
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
269
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
270
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
271
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
272
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
273
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
274
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
275
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
276
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
277
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
278
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
279
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
280
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
281
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
282
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
283
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
284
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
285
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334
286
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
287
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667
288
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0
289
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
290
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
291
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
292
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
293
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
294
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
295
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
296
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
297
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
298
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
299
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
300
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
301
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
302
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
303
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
304
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
305
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
306
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
307
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
308
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
309
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
310
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
311
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
312
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
313
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
314
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
315
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
316
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
317
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
318
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
319
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
320
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
321
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
322
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
323
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
324
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
325
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607
326
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
327
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
328
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
329
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
330
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
331
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
332
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
333
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
334
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
335
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
336
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
337
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
338
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.0,1.0
339
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
340
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
341
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
342
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
343
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
344
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
345
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
346
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
347
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
348
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
349
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
350
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
351
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
352
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
353
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
354
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
355
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
356
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
357
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
358
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
359
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
360
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
361
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
362
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
363
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
364
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
365
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
366
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
367
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
368
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
369
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
370
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
371
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
372
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
373
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
374
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
375
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
376
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
377
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
378
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
379
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
380
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
381
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
382
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
383
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
384
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
385
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
386
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
387
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
388
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
389
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
390
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
391
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
392
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
393
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
394
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
395
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
396
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
397
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
398
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
399
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
400
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
401
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
402
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
403
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607
404
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
405
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
406
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
407
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
408
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
409
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
410
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425
411
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
412
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
413
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
414
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
415
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
416
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
417
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
418
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
419
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
420
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
421
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
422
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
423
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
424
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
425
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
426
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
427
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
428
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
429
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
430
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
431
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
432
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
433
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
434
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
435
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
436
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
437
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
438
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
439
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
440
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
441
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
442
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
443
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
444
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
445
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
446
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
447
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
448
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
449
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
450
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
451
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
452
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676
453
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
454
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
455
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
456
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
457
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
458
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
459
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
460
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
461
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
462
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676
463
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
464
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
465
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
466
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7378647873726218,0.07697417298126676
467
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
468
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
469
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
470
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
471
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
472
- aggregate,holistic,planning,biggen_240612,kendall,random,5,0,-0.19999999999999998,0.8166666666666667
473
- aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
474
- aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
475
- aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
476
- aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
477
- aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
478
- aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
479
- aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
480
- aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334
481
- aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
482
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.9999999999999999,0.016666666666666666
483
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
484
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
485
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
486
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
487
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
488
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
489
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
490
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
491
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
492
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
493
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
494
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
495
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
496
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
497
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
498
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
499
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
500
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
501
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
502
- aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
503
- aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0
504
- aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
505
- aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
506
- aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.7999999999999999,0.08333333333333333
507
- aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
508
- aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
509
- aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
510
- aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
511
- aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0
512
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
513
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
514
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
515
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
516
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.19999999999999998,0.8166666666666667
517
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
518
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
519
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
520
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
521
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
522
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.0,1.0
523
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
524
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
525
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
526
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
527
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
528
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
529
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
530
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
531
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
532
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
533
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
534
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
535
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
536
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
537
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
538
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
539
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
540
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
541
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
542
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
543
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
544
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
545
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
546
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
547
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
548
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
549
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
550
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
551
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
552
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
553
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
554
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
555
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263
556
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
557
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
558
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263
559
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263
560
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425
561
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
562
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
563
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
564
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
565
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
566
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
567
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
568
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
569
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
570
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
571
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
572
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
573
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
574
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
575
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
576
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
577
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
578
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
579
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
580
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
581
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
582
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,0,0.9999999999999999,0.016666666666666666
583
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
584
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
585
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
586
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666
587
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
588
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
589
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
590
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
591
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
592
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
593
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
594
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
595
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
596
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
597
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
598
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
599
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
600
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
601
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
602
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
603
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
604
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
605
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
606
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
607
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
608
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
609
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
610
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
611
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
612
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
613
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
614
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
615
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
616
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
617
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
618
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
619
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334
620
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
621
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334
622
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
623
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
624
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
625
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
626
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
627
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
628
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
629
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334
630
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
631
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334
632
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
633
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
634
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
635
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
636
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
637
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
638
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
639
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
640
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
641
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
642
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
643
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
644
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
645
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
646
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
647
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
648
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
649
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
650
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
651
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
652
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334
653
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,1,0.6,0.23333333333333334
654
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,2,0.19999999999999998,0.8166666666666667
655
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,3,0.19999999999999998,0.8166666666666667
656
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666
657
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,5,0.6,0.23333333333333334
658
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
659
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
660
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,8,0.9999999999999999,0.016666666666666666
661
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334
662
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334
663
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,1,0.39999999999999997,0.48333333333333334
664
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,2,0.39999999999999997,0.48333333333333334
665
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
666
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
667
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,5,0.39999999999999997,0.48333333333333334
668
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,6,0.6,0.23333333333333334
669
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,7,0.19999999999999998,0.8166666666666667
670
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
671
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334
672
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
673
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
674
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
675
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
676
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
677
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
678
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
679
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
680
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
681
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
682
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676
683
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
684
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676
685
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
686
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
687
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
688
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
689
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
690
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
691
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
692
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425
693
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
694
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425
695
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
696
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
697
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
698
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
699
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
700
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
701
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
702
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
703
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
704
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
705
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
706
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
707
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
708
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
709
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
710
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
711
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
712
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
713
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
714
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
715
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
716
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
717
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
718
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
719
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
720
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
721
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
722
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
723
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
724
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
725
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
726
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
727
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
728
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
729
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334
730
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
731
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
732
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
733
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667
734
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
735
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334
736
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667
737
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667
738
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0
739
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
740
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667
741
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
742
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334
743
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.6,0.23333333333333334
744
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333
745
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333
746
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
747
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334
748
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333
749
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333
750
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
751
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334
752
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
753
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
754
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
755
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
756
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
757
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
758
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
759
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
760
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
761
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
762
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
763
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
764
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
765
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
766
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
767
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
768
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
769
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
770
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
771
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
772
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
773
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
774
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
775
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607
776
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
777
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
778
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
779
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
780
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
781
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
782
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
783
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
784
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
785
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
786
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
787
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
788
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.0,1.0
789
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
790
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
791
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
792
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
793
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
794
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
795
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
796
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
797
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
798
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
799
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
800
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
801
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
802
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
803
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
804
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
805
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
806
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
807
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
808
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
809
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
810
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
811
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
812
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
813
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
814
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
815
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
816
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
817
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
818
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
819
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
820
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
821
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
822
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
823
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
824
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
825
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
826
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
827
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
828
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
829
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
830
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
831
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
832
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
833
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
834
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
835
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
836
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
837
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
838
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
839
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
840
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
841
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
842
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
843
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
844
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
845
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
846
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
847
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
848
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
849
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
850
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
851
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
852
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
853
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607
854
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
855
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
856
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607
857
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
858
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
859
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
860
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.5270462766947298,0.206507295485425
861
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
862
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
863
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
864
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
865
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
866
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
867
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
868
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
869
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
870
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
871
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
872
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
873
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
874
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
875
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
876
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
877
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
878
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
879
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
880
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
881
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
882
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
883
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
884
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
885
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
886
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
887
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
888
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
889
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
890
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
891
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
892
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
893
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
894
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
895
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
896
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
897
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
898
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
899
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
900
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
901
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache/agreements_cache_b002484b092f2f62850354386e68e83e.csv DELETED
@@ -1,921 +0,0 @@
1
- scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
2
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
3
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
4
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
5
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
6
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
7
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
8
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
9
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
10
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
11
- grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
12
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
13
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
14
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
15
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
16
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676
17
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
18
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
19
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
20
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
21
- instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
22
- planning,biggen_240612,aggregate,holistic,kendall,random,5,0,-0.19999999999999998,0.8166666666666667
23
- planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
24
- planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
25
- planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
26
- planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
27
- planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
28
- planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
29
- planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
30
- planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
31
- planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
32
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
33
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
34
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
35
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
36
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
37
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
38
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
39
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
40
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
41
- reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
42
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667
43
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
44
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
45
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
46
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
47
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
48
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
49
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
50
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
51
- refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
52
- safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
53
- safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0
54
- safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
55
- safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
56
- safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.7999999999999999,0.08333333333333333
57
- safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
58
- safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
59
- safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
60
- safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
61
- safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0
62
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
63
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
64
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
65
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
66
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
67
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
68
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
69
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
70
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
71
- theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
72
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0
73
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
74
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
75
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
76
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
77
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
78
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
79
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
80
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
81
- tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
82
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
83
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
84
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
85
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
86
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
87
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
88
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334
89
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
90
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
91
- hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
92
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
93
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
94
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
95
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
96
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
97
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
98
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
99
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
100
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
101
- humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
102
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
103
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
104
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
105
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263
106
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
107
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
108
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263
109
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263
110
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425
111
- mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
112
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
113
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
114
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
115
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
116
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
117
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
118
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
119
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
120
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
121
- winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
122
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
123
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
124
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
125
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
126
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
127
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
128
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
129
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
130
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
131
- mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
132
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
133
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
134
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
135
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
136
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
137
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
138
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
139
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
140
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
141
- arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
142
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
143
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
144
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
145
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
146
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
147
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
148
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
149
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
150
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
151
- triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
152
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
153
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
154
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
155
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
156
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
157
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
158
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
159
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
160
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
161
- mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
162
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
163
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
164
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
165
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
166
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
167
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
168
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
169
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
170
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
171
- drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
172
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
173
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
174
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
175
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
176
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
177
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
178
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
179
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
180
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
181
- hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
182
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
183
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
184
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
185
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
186
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
187
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
188
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
189
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
190
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
191
- commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
192
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
193
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
194
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
195
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
196
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
197
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
198
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
199
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
200
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
201
- triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
202
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
203
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
204
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667
205
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.19999999999999998,0.8166666666666667
206
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
207
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
208
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
209
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
210
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
211
- mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
212
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
213
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334
214
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
215
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
216
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334
217
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
218
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
219
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
220
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
221
- drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334
222
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
223
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
224
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
225
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
226
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
227
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
228
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
229
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
230
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
231
- livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
232
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676
233
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
234
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676
235
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425
236
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
237
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
238
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
239
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
240
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
241
- reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
242
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425
243
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676
244
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425
245
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174
246
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
247
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676
248
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
249
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
250
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
251
- coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
252
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
253
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
254
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
255
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
256
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
257
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
258
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
259
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
260
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
261
- mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
262
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
263
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
264
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
265
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
266
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
267
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
268
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
269
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
270
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
271
- data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
272
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
273
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
274
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
275
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
276
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
277
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
278
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
279
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
280
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
281
- language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
282
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
283
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667
284
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
285
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334
286
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667
287
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667
288
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0
289
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
290
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667
291
- if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
292
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
293
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
294
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334
295
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334
296
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
297
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
298
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
299
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
300
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
301
- mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
302
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334
303
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
304
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
305
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
306
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
307
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
308
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
309
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
310
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
311
- arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
312
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
313
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
314
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
315
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
316
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
317
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
318
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
319
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
320
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
321
- agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
322
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
323
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
324
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
325
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
326
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
327
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
328
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
329
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
330
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
331
- arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
332
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
333
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
334
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
335
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607
336
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
337
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
338
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
339
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
340
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
341
- alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
342
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
343
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
344
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
345
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
346
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334
347
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
348
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.0,1.0
349
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
350
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
351
- alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
352
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
353
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
354
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
355
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
356
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
357
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
358
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
359
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
360
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
361
- alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
362
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607
363
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
364
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
365
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
366
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
367
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
368
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
369
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334
370
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
371
- arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
372
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334
373
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
374
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
375
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
376
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
377
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
378
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
379
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
380
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
381
- bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
382
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
383
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
384
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
385
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
386
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
387
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
388
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
389
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
390
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
391
- eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
392
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
393
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
394
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
395
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
396
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
397
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
398
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
399
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
400
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
401
- gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
402
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
403
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
404
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
405
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
406
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
407
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
408
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
409
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667
410
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334
411
- hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
412
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666
413
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607
414
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
415
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
416
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607
417
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333
418
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334
419
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666
420
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425
421
- llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
422
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
423
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334
424
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334
425
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334
426
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
427
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
428
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
429
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
430
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334
431
- magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334
432
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
433
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
434
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666
435
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
436
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
437
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334
438
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
439
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334
440
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666
441
- mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
442
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
443
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333
444
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
445
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666
446
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666
447
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334
448
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333
449
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
450
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
451
- mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666
452
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333
453
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666
454
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333
455
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333
456
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333
457
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666
458
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666
459
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333
460
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333
461
- mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333
462
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676
463
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
464
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
465
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
466
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
467
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
468
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
469
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666
470
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666
471
- aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
472
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676
473
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
474
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667
475
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
476
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7378647873726218,0.07697417298126676
477
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676
478
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
479
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
480
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
481
- aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
482
- aggregate,holistic,planning,biggen_240612,kendall,random,5,0,-0.19999999999999998,0.8166666666666667
483
- aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
484
- aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
485
- aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
486
- aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
487
- aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
488
- aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334
489
- aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
490
- aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334
491
- aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
492
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.9999999999999999,0.016666666666666666
493
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
494
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334
495
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
496
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334
497
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666
498
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
499
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
500
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
501
- aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334
502
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667
503
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333
504
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
505
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666
506
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334
507
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
508
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
509
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
510
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
511
- aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
512
- aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334
513
- aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0
514
- aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334
515
- aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
516
- aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.7999999999999999,0.08333333333333333
517
- aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334
518
- aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667
519
- aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334
520
- aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667
521
- aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0
522
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334
523
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334
524
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334
525
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333
526
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.19999999999999998,0.8166666666666667
527
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333
528
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666
529
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333
530
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
531
- aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666
532
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.0,1.0
533
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666
534
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333
535
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334
536
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333
537
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334
538
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333
539
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334
540
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333
541
- aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333
542
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
543
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
544
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
545
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
546
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
547
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
548
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334
549
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
550
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
551
- aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
552
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
553
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
554
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
555
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334
556
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
557
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
558
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
559
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
560
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
561
- aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
562
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
563
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334
564
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334
565
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263
566
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667
567
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
568
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263
569
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263
570
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425
571
- aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334
572
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334
573
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
574
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
575
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
576
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
577
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
578
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
579
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
580
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
581
- aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
582
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
583
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
584
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
585
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
586
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
587
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
588
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
589
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
590
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
591
- aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
592
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,0,0.9999999999999999,0.016666666666666666
593
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
594
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
595
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
596
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666
597
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
598
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
599
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
600
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
601
- aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
602
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
603
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
604
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
605
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
606
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
607
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
608
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
609
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
610
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
611
- aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
612
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
613
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
614
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
615
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
616
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
617
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
618
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
619
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
620
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
621
- aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
622
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
623
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
624
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
625
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
626
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
627
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
628
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
629
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334
630
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
631
- aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334
632
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
633
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333
634
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
635
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
636
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
637
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333
638
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
639
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334
640
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
641
- aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334
642
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
643
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
644
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
645
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
646
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
647
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
648
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
649
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
650
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
651
- aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
652
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334
653
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
654
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
655
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
656
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
657
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
658
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
659
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
660
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
661
- aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
662
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334
663
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,1,0.6,0.23333333333333334
664
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,2,0.19999999999999998,0.8166666666666667
665
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,3,0.19999999999999998,0.8166666666666667
666
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666
667
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,5,0.6,0.23333333333333334
668
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333
669
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666
670
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,8,0.9999999999999999,0.016666666666666666
671
- aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334
672
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334
673
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,1,0.39999999999999997,0.48333333333333334
674
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,2,0.39999999999999997,0.48333333333333334
675
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334
676
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334
677
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,5,0.39999999999999997,0.48333333333333334
678
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,6,0.6,0.23333333333333334
679
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,7,0.19999999999999998,0.8166666666666667
680
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334
681
- aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334
682
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
683
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
684
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
685
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334
686
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
687
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
688
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
689
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
690
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
691
- aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
692
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676
693
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
694
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676
695
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425
696
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
697
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
698
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
699
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
700
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
701
- aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
702
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425
703
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676
704
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425
705
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174
706
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
707
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676
708
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
709
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
710
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
711
- aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
712
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334
713
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666
714
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
715
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
716
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334
717
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666
718
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
719
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
720
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334
721
- aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666
722
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
723
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333
724
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333
725
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
726
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
727
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333
728
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333
729
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333
730
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
731
- aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333
732
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333
733
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334
734
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334
735
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334
736
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333
737
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334
738
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334
739
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334
740
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333
741
- aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
742
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334
743
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667
744
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667
745
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334
746
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667
747
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667
748
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0
749
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334
750
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667
751
- aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334
752
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,0,0.6,0.23333333333333334
753
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,1,0.7999999999999999,0.08333333333333333
754
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,2,0.6,0.23333333333333334
755
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,3,0.39999999999999997,0.48333333333333334
756
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,4,0.6,0.23333333333333334
757
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,5,0.7999999999999999,0.08333333333333333
758
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,6,0.6,0.23333333333333334
759
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,7,0.7999999999999999,0.08333333333333333
760
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,8,0.6,0.23333333333333334
761
- aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,9,0.7999999999999999,0.08333333333333333
762
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334
763
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.6,0.23333333333333334
764
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333
765
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333
766
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333
767
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334
768
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333
769
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333
770
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666
771
- aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334
772
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
773
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
774
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
775
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
776
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
777
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
778
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
779
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
780
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
781
- aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
782
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
783
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
784
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
785
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
786
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
787
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
788
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
789
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
790
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
791
- aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
792
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
793
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
794
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
795
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607
796
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
797
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
798
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
799
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
800
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
801
- aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
802
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
803
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
804
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
805
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
806
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334
807
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
808
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.0,1.0
809
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
810
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
811
- aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
812
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
813
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
814
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
815
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
816
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
817
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
818
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
819
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
820
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
821
- aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
822
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607
823
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
824
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
825
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
826
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
827
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
828
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
829
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334
830
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
831
- aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
832
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334
833
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
834
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
835
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
836
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
837
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
838
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
839
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
840
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
841
- aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
842
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
843
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
844
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
845
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
846
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
847
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
848
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
849
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
850
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
851
- aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
852
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
853
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
854
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
855
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
856
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
857
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
858
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
859
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
860
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
861
- aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
862
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
863
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
864
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
865
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
866
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
867
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
868
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
869
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667
870
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334
871
- aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
872
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666
873
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607
874
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
875
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
876
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607
877
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333
878
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334
879
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666
880
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.5270462766947298,0.206507295485425
881
- aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333
882
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
883
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334
884
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334
885
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334
886
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
887
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666
888
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
889
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
890
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334
891
- aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334
892
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
893
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666
894
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666
895
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333
896
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333
897
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334
898
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666
899
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334
900
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666
901
- aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
902
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333
903
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333
904
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333
905
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666
906
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666
907
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334
908
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333
909
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333
910
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333
911
- aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666
912
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333
913
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666
914
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333
915
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333
916
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333
917
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666
918
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666
919
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333
920
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333
921
- aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cache/agreements_cache_bdd8d629730630ed8e73cb56f53f335b.csv ADDED
The diff for this file is too large to render. See raw diff