FrontierCode 1.0 Extended - Score
Code · 2026-06-08
FrontierCode 1.0 Extended weighted score across the full set of 150 production-code 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 | 61.6 |
| Opus 4.8 | 51.8 |
| GPT-5.5 | 44.8 |
| Opus 4.7 | 43.9 |
| Kimi K2.7 Code | 39.9 |
| GLM-5.2 | 39.0 |
| Sonnet 5 | 38.8 |
| Kimi K2.6 | 37.0 |
| GPT-5.4 Mini | 36.0 |
| Gemini 3.1 Pro Preview | 34.2 |
| Sonnet 4.6 | 33.6 |
| Kimi K2.5 | 22.7 |
| Qwen3.6 Plus (2026-04-02) | 21.3 |
| MiniMax M2.7 | 19.9 |
| SWE-1.6 | 18.4 |
| MiniMax M2.5 | 15.8 |
| Gemini 3.1 Flash-Lite Preview | 14.6 |