Mathematical Reasoning on CMIMC25 (Accuracy)
52.19AccuracyKnowRL-Nemotron-1.5B
Evaluation Results
| Method | Links | |
|---|---|---|
| KnowRL-Nemotron-1.5BHint Setting=CSS, Evaluation Protocol=mean@322026.04 | 52.19 | |
| KnowRL-Nemotron-1.5BHint Setting=CBRS, Evaluation Protocol=mean@322026.04 | 49.22 | |
| QuestAHint Setting=CSS, Evaluation Protocol=mean@322026.04 | 47.64 | |
| QuestAHint Setting=CBRS, Evaluation Protocol=mean@322026.04 | 46.12 | |
| JustRLHint Setting=CSS, Evaluation Protocol=mean@322026.04 | 45.19 | |
| JustRLHint Setting=CBRS, Evaluation Protocol=mean@322026.04 | 44.45 | |
| KnowRL-Nemotron-1.5BHint Setting=w/o KP, Evaluation Protocol=mean@322026.04 | 44.14 | |
| JustRLHint Setting=w/o KP, Evaluation Protocol=mean@322026.04 | 41.72 | |
| QuestAHint Setting=w/o KP, Evaluation Protocol=mean@322026.04 | 41.48 | |
| Nemotron-1.5BHint Setting=CSS, Evaluation Protocol=mean@322026.04 | 36.7 | |
| Nemotron-1.5BHint Setting=CBRS, Evaluation Protocol=mean@322026.04 | 33.57 | |
| Nemotron-1.5BHint Setting=w/o KP, Evaluation Protocol=mean@322026.04 | 30.08 |