eval-results/leaderboard/xverse7b/xverse7b.json

{"config": {"model_dtype": "", "model_name": "xverse7b", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.32}, "Calculus USS": {"Acc": 0.26}, "Chemistry USS": {"Acc": 0.27}, "Discrete Mathematics USS": {"Acc": 0.23}, "Economy USS": {"Acc": 0.25}, "Geography USS": {"Acc": 0.31}, "Geology USS": {"Acc": 0.23}, "Geometry USS": {"Acc": 0.28}, "History USS": {"Acc": 0.29}, "Logic USS": {"Acc": 0.29}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.22}, "Mathematics LPS": {"Acc": 0.32}, "Mathematics LSS": {"Acc": 0.26}, "Mathematics UPS": {"Acc": 0.27}, "Mathematics USS": {"Acc": 0.25}, "Mathematics and Statistics USS": {"Acc": 0.28}, "Natural Sciences LPS": {"Acc": 0.4}, "Natural Sciences LSS": {"Acc": 0.29}, "Natural Sciences UPS": {"Acc": 0.32}, "Persian Literature LPS": {"Acc": 0.3}, "Persian Literature LSS": {"Acc": 0.28}, "Persian Literature UPS": {"Acc": 0.28}, "Persian Literature USS": {"Acc": 0.26}, "Philosophy USS": {"Acc": 0.26}, "Physics USS": {"Acc": 0.24}, "Probability and Statistics USS": {"Acc": 0.24}, "Psychology USS": {"Acc": 0.35}, "Social Studies LPS": {"Acc": 0.44}, "Social Studies LSS": {"Acc": 0.34}, "Social Studies UPS": {"Acc": 0.36}, "Sociology USS": {"Acc": 0.28}, "Speed and Accuracy UPS": {"Acc": 0.26}, "Theology LPS": {"Acc": 0.44}, "Theology LSS": {"Acc": 0.34}, "Theology UPS": {"Acc": 0.38}, "Theology USS": {"Acc": 0.28}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.27}, "\u200cBiology USS": {"Acc": 0.28}, "Avg on all tasks": {"Acc": 0.3}, "Avg on all questions": {"Acc": 0.29}}}