GSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-domain Evaluation | GSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA USMLE | Math Accuracy30.65 | 24 |
Showing 1 of 1 rows