Reasoning Evaluation Suite
Benchmarks
TaskDatasetSOTA resultTrendResults
Reasoning Evaluation Suite (GSM8K, MATH500, AIME24, HumanEval) (test)
94.7GSM8K Accuracy
36
Reasoning Evaluation Suite Math, Symbolic, and Commonsense (test)
80.8Math Accuracy
33
Reasoning Evaluation Suite AIME 2024, GSM8k, MATH 500, GPQA
60AIME 2024 Score
32
Reasoning Evaluation Suite (MATH, GSM8K, AQUA, GSM-H, MMLU, MMLU-P, AIME) (test)
52.4MATH Score
8