Mathematical Reasoning on HMMT25 Nov.
57.5Pass@1GPT-5.2-chat (teacher)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2-chat (teacher)2026.05 | 57.5 | |
| Qwen3-30B-A3B (teacher)Access=–2026.05 | 55 | |
| ROPDThinking Mode=Thinking2026.05 | 54.17 | |
| T-JudgeThinking Mode=Thinking2026.05 | 51.25 | |
| OVDThinking Mode=Thinking2026.05 | 50.42 | |
| GADThinking Mode=Thinking2026.05 | 49.58 | |
| Qwen3-4B (student)Thinking Mode=Thinking2026.05 | 48.75 | |
| ROPDThinking Mode=Non-Thinking2026.05 | 41.67 | |
| ROPDAccess=text2026.05 | 38.8 | |
| T-JudgeThinking Mode=Non-Thinking2026.05 | 38.75 | |
| OVDThinking Mode=Non-Thinking2026.05 | 37.92 | |
| ExOPDAccess=logit2026.05 | 26.68 | |
| LOPDAccess=logit2026.05 | 24.17 | |
| GADThinking Mode=Non-Thinking2026.05 | 14.11 | |
| SFTAccess=text2026.05 | 8.33 | |
| Qwen3-4B (student)Thinking Mode=Non-Thinking2026.05 | 7.08 | |
| Qwen3-4B (student)Access=–2026.05 | 7.08 |