FrontierCode 1.0 Main - Score
Code · 2026-06-08
FrontierCode 1.0 Main weighted score on the 100 hardest tasks in the 150-task Extended set, including all 50 Diamond tasks. Maintainer-authored rubrics cover correctness, regression safety, test quality, scope, and code quality; a trial that fails any blocker criterion receives a zero score.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Fable 5 | 46.8 |
| Opus 4.8 | 34.3 |
| GPT-5.5 | 25.5 |
| Opus 4.7 | 23.8 |
| Kimi K2.7 Code | 22.0 |
| GLM-5.2 | 19.2 |
| GPT-5.4 Mini | 17.8 |
| Gemini 3.1 Pro Preview | 16.7 |
| Kimi K2.6 | 16.0 |
| Sonnet 4.6 | 15.1 |
| Qwen3.6 Plus (2026-04-02) | 9.7 |
| Kimi K2.5 | 6.9 |
| MiniMax M2.7 | 6.0 |
| SWE-1.6 | 5.5 |
| MiniMax M2.5 | 5.3 |
| Gemini 3.1 Flash-Lite Preview | 4.8 |