Code Reasoning (Output Prediction) on CruxEval-O
36.4CX-O ScoreCodeEnhance+CodeQA
Evaluation Results
| Method | Links | |
|---|---|---|
| CodeEnhance+CodeQATokens (B)=102026.06 | 36.4 | |
| 90% CodeEnhance+CodeQA + 10% RawTokens (B)=102026.06 | 35.2 | |
| 95% CodeEnhance+CodeQA + 5% RawTokens (B)=102026.06 | 35.1 | |
| CodeEnhance-gemma-4bTokens (B)=102026.06 | 34.5 | |
| CodeEnhance+Nemotron-RW+SwallowCodeTokens (B)=102026.06 | 33.8 | |
| CodeEnhanceTokens (B)=102026.06 | 33.2 | |
| 50% CodeEnhance + 50% Nemotron-RWTokens (B)=102026.06 | 33.2 | |
| Nemotron-RWTokens (B)=102026.06 | 31.9 | |
| SwallowCodeTokens (B)=102026.06 | 31.3 | |
| CodeEnhance-gemma-1bTokens (B)=102026.06 | 30.9 |