Mathematical Reasoning on Olympiad Bench (Accuracy, Absolute Improvement, Relative Gain)
29.8AccuracyTTSV
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| TTSVModel=Qwen2.5-Math-7B2025.12 | 29.8 | 13.1 | 78.44 | |
| Qwen2.5-Math-7BModel=Qwen2.5-Math-7B2025.12 | 16.7 | — | — | |
| TTSVModel=LLaMA-3.1-8B2025.12 | 14.2 | 2.6 | 22.41 | |
| LLaMA-3.1-8BModel=LLaMA-3.1-8B2025.12 | 11.6 | — | — | |
| EMModel=Qwen2.5-Math-7B2025.12 | — | 16 | — | |
| EMModel=LLaMA-3.1-8B2025.12 | — | -1.6 | — |