Reasoning on BrUMO25
94.58Pass@1Free()LM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Free()LMBackbone=Qwen3-235B2026.02 | 94.58 | 16,400 | |
| GeminiBackbone=Qwen3-235B2026.02 | 93.75 | 17,700 | |
| No TrainBackbone=Qwen3-235B2026.02 | 92.08 | 17,100 | |
| VanillaBackbone=Qwen3-235B2026.02 | 91.67 | 19,900 | |
| No TrainBackbone=Qwen3-30B2026.02 | 86.25 | 17,100 | |
| Free()LMBackbone=Qwen3-30B2026.02 | 85.42 | 14,000 | |
| GeminiBackbone=Qwen3-30B2026.02 | 84.17 | 15,900 | |
| VanillaBackbone=Qwen3-30B2026.02 | 82.92 | 15,100 | |
| Free()LMBackbone=Qwen3-8B2026.02 | 72.5 | 13,700 | |
| No TrainBackbone=Qwen3-8B2026.02 | 70.83 | 16,400 | |
| H2OBackbone=Qwen3-8B2026.02 | 70 | 18,300 | |
| VanillaBackbone=Qwen3-8B2026.02 | 69.58 | 15,800 | |
| GeminiBackbone=Qwen3-8B2026.02 | 68.75 | 15,200 | |
| TCBackbone=Qwen3-8B2026.02 | 66.67 | 16,600 |