Code Generation on LCB v6 (Score)
84.5ScoreConfident Decoding
Evaluation Results
| Method | Links | |
|---|---|---|
| Confident DecodingModel=gpt-oss-120B, Decoding Method=Confident2026.06 | 84.5 | |
| Last Layer DecodingModel=gpt-oss-120B, Decoding Method=Last Layer2026.06 | 83.1 | |
| Confident DecodingModel=Qwen3.5-122B-A10B, Decoding Method=Confident2026.06 | 79.2 | |
| Confident DecodingModel=Gemma-4-31B, Decoding Method=Confident2026.06 | 78.3 | |
| Confident DecodingModel=gpt-oss-20b, Decoding Method=Confident2026.06 | 78 | |
| Last Layer DecodingModel=gpt-oss-20b, Decoding Method=Last Layer2026.06 | 77.4 | |
| Last Layer DecodingModel=Qwen3.5-122B-A10B, Decoding Method=Last Layer2026.06 | 76.8 | |
| Confident DecodingModel=Qwen3.5-35B-A3B, Decoding Method=Confident2026.06 | 75.1 | |
| Last Layer DecodingModel=Gemma-4-31B, Decoding Method=Last Layer2026.06 | 75.1 | |
| Confident DecodingModel=Qwen3.5-27B, Decoding Method=Confident2026.06 | 73.8 | |
| Last Layer DecodingModel=Qwen3.5-35B-A3B, Decoding Method=Last Layer2026.06 | 70 | |
| Last Layer DecodingModel=Qwen3.5-27B, Decoding Method=Last Layer2026.06 | 63.7 | |
| Confident DecodingModel=Qwen3.5-9B-Base, Decoding Method=Confident2026.06 | 50.5 | |
| Last Layer DecodingModel=Qwen3.5-9B-Base, Decoding Method=Last Layer2026.06 | 49.1 | |
| Confident DecodingModel=Qwen3.5-9B, Decoding Method=Confident2026.06 | 47.7 | |
| Last Layer DecodingModel=Qwen3.5-9B, Decoding Method=Last Layer2026.06 | 41.1 | |
| Last Layer DecodingModel=Qwen3.5-0.8B, Decoding Method=Last Layer2026.06 | 0 | |
| Confident DecodingModel=Qwen3.5-0.8B, Decoding Method=Confident2026.06 | 0 |