Reasoning on IMOAnswer
62.75Pass@1Free()LM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Free()LMBackbone=Qwen3-235B2026.02 | 62.75 | 24,200 | |
| GeminiBackbone=Qwen3-235B2026.02 | 62.25 | 27,600 | |
| VanillaBackbone=Qwen3-235B2026.02 | 61 | 32,300 | |
| No TrainBackbone=Qwen3-235B2026.02 | 58.25 | 24,400 | |
| Free()LMBackbone=Qwen3-30B2026.02 | 58 | 18,100 | |
| GeminiBackbone=Qwen3-30B2026.02 | 54 | 20,400 | |
| No TrainBackbone=Qwen3-30B2026.02 | 53.25 | 19,400 | |
| VanillaBackbone=Qwen3-30B2026.02 | 52.25 | 21,100 | |
| Free()LMBackbone=Qwen3-8B2026.02 | 40.5 | 14,300 | |
| GeminiBackbone=Qwen3-8B2026.02 | 40 | 17,800 | |
| No TrainBackbone=Qwen3-8B2026.02 | 38.75 | 17,400 | |
| VanillaBackbone=Qwen3-8B2026.02 | 38.5 | 19,400 | |
| H2OBackbone=Qwen3-8B2026.02 | 36.25 | 20,700 | |
| TCBackbone=Qwen3-8B2026.02 | 34 | 20,300 |