Code Generation on Leetcode-New
49.08Pass RateGemini-2.0-Flash
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Gemini-2.0-FlashProcessing=Postprocessed2026.01 | 49.08 | 48.47 | 2.45 | |
| GPT-4.1-MiniProcessing=Postprocessed2026.01 | 48.47 | 42.33 | 9.2 | |
| o4-miniProcessing=Postprocessed2026.01 | 48.47 | 49.08 | 2.45 | |
| GPT-4.1-MiniProcessing=Filtered2026.01 | 45.28 | 38.24 | 16.47 | |
| Gemini-2.0-FlashProcessing=Filtered2026.01 | 44.71 | 54.12 | 1.18 | |
| Claude 3.7 SonnetProcessing=Filtered2026.01 | 44.71 | 54.71 | 0.59 | |
| Claude 3.7 SonnetProcessing=Postprocessed2026.01 | 42.33 | 57.67 | 0 | |
| o4-miniProcessing=Filtered2026.01 | 40.59 | 58.82 | 0.59 | |
| Qwen2.5-7b-InstructProcessing=Filtered2026.01 | 25.29 | 74.12 | 0.59 | |
| Qwen2.5-7b-InstructProcessing=Postprocessed2026.01 | 22.7 | 75.46 | 1.84 | |
| Qwen2.5-3b-CoderProcessing=Postprocessed2026.01 | 20.25 | 66.87 | 12.88 | |
| Qwen2.5-3b-CoderProcessing=Filtered2026.01 | 18.24 | 62.94 | 18.82 |