Mathematics on AMC 23 (pass@1)
80.79Pass@1DS
Evaluation results
| Method | Links | |
|---|---|---|
| DSModel=R1-DISTILL-QWEN-7B2026.03 | 80.79 | |
| INSIGHTModel=QWEN3-4B2026.03 | 79 | |
| INSIGHTModel=R1-DISTILL-QWEN-7B2026.03 | 78.4 | |
| EXPECTED-DIFFICULTYModel=R1-DISTILL-QWEN-7B2026.03 | 78.1 | |
| RANDOMModel=QWEN3-4B2026.03 | 78.01 | |
| RANDOMModel=R1-DISTILL-QWEN-7B2026.03 | 77.9 | |
| MoPPSModel=R1-DISTILL-QWEN-7B2026.03 | 77.86 | |
| INVERSE-EVIDENCEModel=R1-DISTILL-QWEN-7B2026.03 | 77.7 | |
| MoPPSModel=QWEN3-4B2026.03 | 77.41 | |
| INVERSE-EVIDENCEModel=QWEN3-4B2026.03 | 77.18 | |
| INSIGHTModel=QWEN3-0.6B2026.03 | 44.3 | |
| MoPPSModel=QWEN3-0.6B2026.03 | 44.16 | |
| RANDOMModel=QWEN3-0.6B2026.03 | 43.9 | |
| INVERSE-EVIDENCEModel=QWEN3-0.6B2026.03 | 42.5 |