Math Reasoning on AIME 2025 (Score)
100ScoreGPT-5.2
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.22026.03 | 100 | |
| Kimi-K2.5Number of Parameters=1T-A32B2026.03 | 96.1 | |
| Gemini-3-Pro2026.03 | 95 | |
| Intern-S1-ProNumber of Parameters=1T-A22B2026.03 | 93.1 | |
| Qwen3-VL-235B-ThinkingNumber of Parameters=235B-A22B, Thinking Configuration=true2026.03 | 90 | |
| Soft-RLVRVerifier=GPT-OSS-20B, Checklist source=DeepSeek R1, Training step=5002026.05 | 28.67 | |
| Soft-RLVRVerifier=GPT-OSS-120B, Checklist source=DeepSeek R1, Training step=5002026.05 | 28.5 | |
| Oracle rule-basedReward=Oracle rule-based, Training step=5002026.05 | 28 | |
| Command R7B (No RL)Reward=None (Initial Policy), Training step=5002026.05 | 27.33 |