Mathematical Reasoning on AIME 2025 (PASS@1, R, Delta)
52.4PASS@1Gemini-2.5-F
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini-2.5-FModel=Gemini-2.5-Flash2025.10 | 52.4 | 17 | 35.4 | |
| Qwen3-30BModel=Qwen3-30B2025.10 | 43.1 | 15.8 | 27.3 | |
| Gemini-2.5-F-LModel=Gemini-2.5-Flash-Lite2025.10 | 37.4 | 15.9 | 21.5 | |
| GPT-4.1-MModel=GPT-4.1-mini2025.10 | 30.5 | 20.9 | 9.6 | |
| GPT-4.1Model=GPT-4.12025.10 | 26.5 | 16.8 | 9.7 |