Mathematical Reasoning on AIME 2025 (pass@1, pass@10)
66.7Pass@1Qwen3-8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-8BParameters=8B2025.10 | 66.7 | 81.3 | |
| Qwen3-4BParameters=4B2025.10 | 51.3 | 63.3 | |
| Ouro-2.6B-Thinking-R4Parameters=2.6B, Configuration=Thinking-R42025.10 | 50.3 | 76.7 | |
| Ouro-1.4B-Thinking-R4Parameters=1.4B, Configuration=Thinking-R42025.10 | 46.3 | 73.3 | |
| Deepseek-Distill-Qwen-7BParameters=7B2025.10 | 36 | 73.3 | |
| Deepseek-Distill-Qwen-1.5BParameters=1.5B2025.10 | 23 | 43.33 | |
| Qwen3-1.7BParameters=1.7B2025.10 | 22 | 33.3 |