Mathematical Reasoning on HMMT25 (avg@8)
53.33Avg@8 ScoreMTI
Evaluation results
| Method | Links | |
|---|---|---|
| MTIModel Series=Qwen3-8B2026.02 | 53.33 | |
| CCDModel Series=Qwen3-14B2026.02 | 50.83 | |
| MTIModel Series=Qwen3-14B2026.02 | 50.21 | |
| BaseModel Series=Qwen3-14B, Decoding Mode=Standard decoding2026.02 | 49.17 | |
| CCDModel Series=Qwen3-8B2026.02 | 47.92 | |
| CCDModel Series=Qwen3-4B2026.02 | 46.25 | |
| BaseModel Series=Qwen3-8B, Decoding Mode=Standard decoding2026.02 | 44.58 | |
| BaseModel Series=Qwen3-4B, Decoding Mode=Standard decoding2026.02 | 42.92 | |
| MTIModel Series=Qwen3-4B2026.02 | 40 | |
| NPR (Variant)Data=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.12 | 32.9 | |
| Qwen3-4B-Instruct-2507Data=N/A, Train=N/A, Base=N/A2025.12 | 31 | |
| NPRData=orz-8k, Train=Parallel RL, Base=NPR-BETA2025.12 | 30.8 | |
| NPR-BETA (Variant)Data=orz-8k, Train=Parallel SFT, Base=Q3-4B2025.12 | 29.2 | |
| SRData=orz-8k, Train=Sequential RL, Base=NPR-BETA2025.12 | 26.3 | |
| NPR-BETAData=orz-8k, Train=Parallel SFT, Base=Q3-4B-Inst.2025.12 | 23.3 | |
| SR-BETAData=orz-8k, Train=Sequential SFT, Base=Q3-4B-Inst.2025.12 | 22.5 | |
| Multiverse-32BData=s1.1-8k, Train=S→P SFT, Base=Q2.5-32B-Inst.2025.12 | 20.8 | |
| Multiverse-4BData=s1.1-8k, Train=S→P SFT, Base=Q3-4B-Inst.2025.12 | 20.8 | |
| Qwen3-4B (Non-Thinking)Data=N/A, Train=N/A, Base=N/A2025.12 | 12.1 | |
| Qwen2.5-32B-InstructData=N/A, Train=N/A, Base=N/A2025.12 | 3.8 |