Planning on Countdown (held-out)
87.96Pass@1INSIGHT
Evaluation Results
| Method | Links | |
|---|---|---|
| INSIGHTModel=QWEN3-4B2026.03 | 87.96 | |
| MoPPSModel=QWEN3-4B2026.03 | 87.8 | |
| RANDOMModel=QWEN3-4B2026.03 | 84.9 | |
| INVERSE-EVIDENCEModel=QWEN3-4B2026.03 | 83.59 | |
| DSModel=R1-DISTILL-QWEN-7B2026.03 | 83.05 | |
| INSIGHTModel=R1-DISTILL-QWEN-7B2026.03 | 81.73 | |
| MoPPSModel=R1-DISTILL-QWEN-7B2026.03 | 81.66 | |
| EXPECTED-DIFFICULTYModel=R1-DISTILL-QWEN-7B2026.03 | 81.2 | |
| RANDOMModel=R1-DISTILL-QWEN-7B2026.03 | 79.02 | |
| INVERSE-EVIDENCEModel=R1-DISTILL-QWEN-7B2026.03 | 78.32 | |
| INSIGHTModel=QWEN3-0.6B2026.03 | 76.7 | |
| MoPPSModel=QWEN3-0.6B2026.03 | 76.28 | |
| INVERSE-EVIDENCEModel=QWEN3-0.6B2026.03 | 72.13 | |
| RANDOMModel=QWEN3-0.6B2026.03 | 71.57 |