eval-results/leaderboard/gpt35/gpt35.json

{"config": {"model_dtype": "", "model_name": "gpt35", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.36}, "Calculus USS": {"Acc": 0.26}, "Chemistry USS": {"Acc": 0.31}, "Discrete Mathematics USS": {"Acc": 0.22}, "Economy USS": {"Acc": 0.4}, "Geography USS": {"Acc": 0.38}, "Geology USS": {"Acc": 0.39}, "Geometry USS": {"Acc": 0.3}, "History USS": {"Acc": 0.37}, "Logic USS": {"Acc": 0.31}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.26}, "Mathematics LPS": {"Acc": 0.39}, "Mathematics LSS": {"Acc": 0.32}, "Mathematics UPS": {"Acc": 0.35}, "Mathematics USS": {"Acc": 0.31}, "Mathematics and Statistics USS": {"Acc": 0.34}, "Natural Sciences LPS": {"Acc": 0.61}, "Natural Sciences LSS": {"Acc": 0.39}, "Natural Sciences UPS": {"Acc": 0.5}, "Persian Literature LPS": {"Acc": 0.42}, "Persian Literature LSS": {"Acc": 0.34}, "Persian Literature UPS": {"Acc": 0.38}, "Persian Literature USS": {"Acc": 0.27}, "Philosophy USS": {"Acc": 0.39}, "Physics USS": {"Acc": 0.29}, "Probability and Statistics USS": {"Acc": 0.31}, "Psychology USS": {"Acc": 0.4}, "Social Studies LPS": {"Acc": 0.67}, "Social Studies LSS": {"Acc": 0.43}, "Social Studies UPS": {"Acc": 0.52}, "Sociology USS": {"Acc": 0.33}, "Speed and Accuracy UPS": {"Acc": 0.36}, "Theology LPS": {"Acc": 0.61}, "Theology LSS": {"Acc": 0.45}, "Theology UPS": {"Acc": 0.54}, "Theology USS": {"Acc": 0.34}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.43}, "\u200cBiology USS": {"Acc": 0.3}, "Avg on all tasks": {"Acc": 0.38}, "Avg on all questions": {"Acc": 0.36}}}