| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| []() | 76.01 | NVIDIA Llama Nemotron Ultra v1 | ||
| []() | 72.3 | Openai-o1-preview | ||
| []() | 65 | Claude3.5-Sonnet | ||
| Search-o1: Agentic Search-Enhanced Large Reasoning Models | ✓ Link | 63.6 | Search-o1 | 2025-01-09 |
| TextGrad: Automatic "Differentiation" via Text | ✓ Link | 55 | GPT4o+TextGrad | 2024-06-11 |
| TextGrad: Automatic "Differentiation" via Text | ✓ Link | 53.6 | GPT4o | 2024-06-11 |
| Qwen2.5 Technical Report | ✓ Link | 49 | Qwen2.5-72B-Instruct | 2024-12-19 |