FrontierCode 1.1 Extended - Score
Code · 2026-07-07
FrontierCode 1.1 Extended weighted score across the full set of 150 production-code tasks. The 1.1 methodology adds fair-internet-use instructions and verification, and relaxes overly strict blocker criteria; flagged runs receive zero.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 65.3 |
| Claude Fable 5 | 64.9 |
| GPT-6 Astra | 64.5 |
| Claude Sonnet 5.5 | 64.4 |
| Claude Fable 5.1 | 63.6 |
| SWE-2 | 62.5 |
| Grok 4.6 | 61.3 |
| GPT-6 Sol | 60.7 |
| Gemini 4 Argon | 60.6 |
| GPT-5.6 Sol | 60.5 |
| GPT-6.1 Sol | 60.4 |
| Opus 4.8 | 59.6 |
| Grok 4.7 | 59.4 |
| Claude Haiku 5.5 | 58.4 |
| GPT-5.5 | 56.7 |
| DeepSeek V4.1 Flash | 56.6 |
| Grok 4.5 | 56.6 |
| Gemini 3.7 Flash | 56.3 |
| Sonnet 5 | 56.2 |
| GPT-6 Luna | 56.1 |
| GPT-5.6 Terra | 55.8 |
| GPT-5.6 Luna | 55.1 |
| SWE-1.7 | 54.6 |
| Opus 4.7 | 53.9 |
| Gemini 3.8 Flash | 53.5 |
| Mistral Large 4 Preview | 53.2 |
| GLM-5.3 | 52.6 |
| Gemini 3.6 Flash | 48.0 |
| GLM-5.3 Flash | 46.2 |
| Kimi K2.7 Code | 45.4 |
| DeepSeek V4 Pro 0813 | 44.5 |
| Opus 4.6 | 43.7 |
| GPT-5.4 Mini | 43.0 |
| Composer 2.5 | 40.8 |
| GLM-5.2 | 40.0 |
| Sonnet 4.6 | 40.0 |
| DeepSeek-V4-Flash-0731 | 31.7 |
| DeepSeek-V4-Pro | 31.0 |
| MiniMax M3 | 28.5 |
| Inkling | 24.8 |