Code Generation on Aider Polyglot (Pass@3)
59Pass@3Zero-shot
Evaluation Results
| Method | Links | |
|---|---|---|
| Zero-shotModel=DeepSeek V3.2, Method=Zero-shot2026.04 | 59 | |
| MTL (I)Model=DeepSeek V3.2, Method=MTL (I)2026.04 | 58 | |
| MTL (T)Model=GPT-5-mini, Method=MTL (T)2026.04 | 49 | |
| MTL (I)Model=Qwen3-Coder-480B-A35B-Instruct, Method=MTL (I)2026.04 | 48 | |
| Zero-shotModel=GPT-5-mini, Method=Zero-shot2026.04 | 47 | |
| MTL (W)Model=GPT-5-mini, Method=MTL (W)2026.04 | 47 | |
| MTL (I)Model=GPT-5-mini, Method=MTL (I)2026.04 | 47 | |
| MTL (S)Model=GPT-5-mini, Method=MTL (S)2026.04 | 46 | |
| Zero-shotModel=Qwen3-Coder-480B-A35B-Instruct, Method=Zero-shot2026.04 | 46 |