Vibe Coding on SWE-Bench Pro
55.6Overall ScoreGPT-5.2 High
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2 High2026.06 | 55.6 | |
| Claude-Opus-4.52026.06 | 55.4 | |
| GPT-5-mini High2026.06 | 51.7 | |
| Gemini-3-pro High2026.06 | 49.7 | |
| Claude-Sonnet-4.52026.06 | 48.4 | |
| Seed2.0 Pro2026.06 | 46.9 | |
| Gemini-3-Flash High2026.06 | 46.7 | |
| Seed2.0 Lite2026.06 | 46 |