Code Generation on MBPP+ Advanced persona
95Win-rateGPT-5.1 vs. GPT-4o
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5.1 vs. GPT-4oPrompt Type=Control2026.04 | 95 | 1 | |
| GPT-5.1 vs. GPT-OSS-20BPrompt Type=Control2026.04 | 93 | 1 | |
| GPT-5.1 vs. GPT-OSS-20BPrompt Type=Original2026.04 | 91 | 1 | |
| GPT-5.1 vs. GPT-4oPrompt Type=Original2026.04 | 88 | 0 | |
| GPT-5.1 vs. GPT-4oPrompt Type=Personalized2026.04 | 82 | 2 | |
| Gemini-3-Pro vs. Gemma-3-4BPrompt Type=Personalized2026.04 | 70 | 2 | |
| Gemini-3-Pro vs. Gemma-3-4BPrompt Type=Control2026.04 | 69 | 2 | |
| Gemini-3-Pro vs. Gemma-3-4BPrompt Type=Original2026.04 | 66 | 2 | |
| GPT-5.1 vs. GPT-OSS-20BPrompt Type=Personalized2026.04 | 58 | 3 | |
| Qwen3-32B vs. Qwen3-14BPrompt Type=Personalized2026.04 | 54 | 4 | |
| Qwen3-32B vs. Qwen3-14BPrompt Type=Control2026.04 | 40 | 5 | |
| Qwen3-32B vs. Qwen3-14BPrompt Type=Original2026.04 | 38 | 5 |