eval-results/leaderboard/human/human.json

{"config": {"model_dtype": "", "model_name": "human", "model_sha": ""}, "results": {"Analytical Talent LSS": {"Acc": 0.59}, "Calculus USS": {"Acc": 0.85}, "Chemistry USS": {"Acc": 0.73}, "Discrete Mathematics USS": {"Acc": 0.78}, "Economy USS": {"Acc": 0.69}, "Geography USS": {"Acc": 0.85}, "Geology USS": {"Acc": 0.89}, "Geometry USS": {"Acc": 0.83}, "History USS": {"Acc": 0.85}, "Logic USS": {"Acc": 0.58}, "Mathematical and Logical Intelligence UPS": {"Acc": 0.44}, "Mathematics LPS": {"Acc": 0.77}, "Mathematics LSS": {"Acc": 0.77}, "Mathematics UPS": {"Acc": 0.66}, "Mathematics USS": {"Acc": 0.84}, "Mathematics and Statistics USS": {"Acc": 0.63}, "Natural Sciences LPS": {"Acc": 0.85}, "Natural Sciences LSS": {"Acc": 0.72}, "Natural Sciences UPS": {"Acc": 0.82}, "Persian Literature LPS": {"Acc": 0.83}, "Persian Literature LSS": {"Acc": 0.77}, "Persian Literature UPS": {"Acc": 0.8}, "Persian Literature USS": {"Acc": 0.59}, "Philosophy USS": {"Acc": 0.61}, "Physics USS": {"Acc": 0.83}, "Probability and Statistics USS": {"Acc": 0.77}, "Psychology USS": {"Acc": 0.79}, "Social Studies LPS": {"Acc": 0.94}, "Social Studies LSS": {"Acc": 0.86}, "Social Studies UPS": {"Acc": 0.89}, "Sociology USS": {"Acc": 0.82}, "Speed and Accuracy UPS": {"Acc": 0.84}, "Theology LPS": {"Acc": 0.88}, "Theology LSS": {"Acc": 0.88}, "Theology UPS": {"Acc": 0.9}, "Theology USS": {"Acc": 0.8}, "Verbal and Linguistic Intelligence UPS": {"Acc": 0.63}, "\u200cBiology USS": {"Acc": 0.73}, "Avg on all tasks": {"Acc": 0.77}, "Avg on all questions": {"Acc": 0.77}}}