Mathematical Reasoning on FinanceMath
64AccuracyF-1
Evaluation Results
| Method | Links | |
|---|---|---|
| F-1Model=GPT-5, Model Category=Proprietary2026.01 | 64 | |
| F-1Model=Qwen3-235B, Model Category=Open Source2026.01 | 61 | |
| PoTModel=Qwen3-235B, Model Category=Open Source2026.01 | 59.5 | |
| F-1Model=Gemini 2.5 Pro, Model Category=Proprietary2026.01 | 56.5 | |
| CoTModel=Gemini 2.5 Pro, Model Category=Proprietary2026.01 | 56 | |
| F-1Model=Qwen3-30B, Model Category=Open Source2026.01 | 56 | |
| PoTModel=Gemini 2.5 Pro, Model Category=Proprietary2026.01 | 55.5 | |
| PoTModel=GPT-5, Model Category=Proprietary2026.01 | 54 | |
| CoTModel=Qwen3-30B, Model Category=Open Source2026.01 | 53.5 | |
| PoTModel=Qwen3-30B, Model Category=Open Source2026.01 | 53.5 | |
| F-1Model=DeepSeek-V3.1, Model Category=Open Source2026.01 | 44 | |
| CoTModel=GPT-5, Model Category=Proprietary2026.01 | 42.5 | |
| PoTModel=DeepSeek-V3.1, Model Category=Open Source2026.01 | 37.5 | |
| Zero-ShotModel=Qwen3-235B, Model Category=Open Source2026.01 | 35.5 | |
| CoTModel=Qwen3-235B, Model Category=Open Source2026.01 | 35 | |
| Zero-ShotModel=Gemini 2.5 Pro, Model Category=Proprietary2026.01 | 32.5 | |
| Zero-ShotModel=Qwen3-30B, Model Category=Open Source2026.01 | 28.5 | |
| CoTModel=DeepSeek-V3.1, Model Category=Open Source2026.01 | 28 | |
| Zero-ShotModel=DeepSeek-V3.1, Model Category=Open Source2026.01 | 27.5 | |
| Zero-ShotModel=GPT-5, Model Category=Proprietary2026.01 | 26 |