List your company

Reasoning Datasets

Benchmarks

TaskDatasetSOTA resultTrendResults
Reasoning Datasets Average (MATH500, OlympiadBench, MinervaMath, GSM8K, MMLU)
58.1Accuracy
21
Reasoning Datasets GSM8K, Math, AIME2024, HumanEval, LiveCodeBench
87.23GSM8K
9