eval-results/leaderboard/xverse13b/xverse13b.json

{"config": {"model_dtype": "", "model_name": "xverse13b", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.29}, "Calculus USS": {"Acc": 0.25}, "Chemistry USS": {"Acc": 0.28}, "Discrete Mathematics USS": {"Acc": 0.24}, "Economy USS": {"Acc": 0.33}, "Geography USS": {"Acc": 0.3}, "Geology USS": {"Acc": 0.32}, "Geometry USS": {"Acc": 0.27}, "History USS": {"Acc": 0.33}, "Logic USS": {"Acc": 0.33}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.22}, "Mathematics LPS": {"Acc": 0.33}, "Mathematics LSS": {"Acc": 0.31}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.24}, "Mathematics and Statistics USS": {"Acc": 0.28}, "Natural Sciences LPS": {"Acc": 0.48}, "Natural Sciences LSS": {"Acc": 0.32}, "Natural Sciences UPS": {"Acc": 0.39}, "Persian Literature LPS": {"Acc": 0.39}, "Persian Literature LSS": {"Acc": 0.29}, "Persian Literature UPS": {"Acc": 0.35}, "Persian Literature USS": {"Acc": 0.25}, "Philosophy USS": {"Acc": 0.31}, "Physics USS": {"Acc": 0.28}, "Probability and Statistics USS": {"Acc": 0.25}, "Psychology USS": {"Acc": 0.32}, "Social Studies LPS": {"Acc": 0.59}, "Social Studies LSS": {"Acc": 0.35}, "Social Studies UPS": {"Acc": 0.36}, "Sociology USS": {"Acc": 0.32}, "Speed and Accuracy UPS": {"Acc": 0.29}, "Theology LPS": {"Acc": 0.48}, "Theology LSS": {"Acc": 0.38}, "Theology UPS": {"Acc": 0.41}, "Theology USS": {"Acc": 0.28}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.37}, "\u200cBiology USS": {"Acc": 0.27}, "Avg on all tasks": {"Acc": 0.32}, "Avg on all questions": {"Acc": 0.31}}}