Code Generation on Leetcode Original
38.6Pass Rateo4-mini
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| o4-miniProcessing=Postprocessed2026.01 | 38.6 | 58.77 | 2.63 | |
| GPT-4.1-MiniProcessing=Postprocessed2026.01 | 32.89 | 54.82 | 12.28 | |
| Gemini-2.0-FlashProcessing=Postprocessed2026.01 | 32.46 | 64.47 | 3.07 | |
| Claude 3.7 SonnetProcessing=Postprocessed2026.01 | 31.14 | 67.11 | 1.75 | |
| Qwen2.5-7b-InstructProcessing=Postprocessed2026.01 | 11.84 | 83.77 | 4.39 | |
| Qwen2.5-3b-CoderProcessing=Postprocessed2026.01 | 2.63 | 85.53 | 11.84 |