Atlas

Benchmarks

← All benchmarks

FrontierCode 1.1 Main - Pass Rate

Code · 2026-07-07

FrontierCode 1.1 Main pass rate on the 100 hardest tasks in the 150-task Extended set. A trial passes only when it satisfies every blocker criterion and is not flagged for unfair internet use.

Top models (higher is better)

ModelScore
Claude Fable 558.9
Claude Opus 558.9
GPT-5.6 Sol52.9
Opus 4.851.6
GPT-5.548.2
SWE-1.747.8
Sonnet 547.6
Grok 4.547.2
GPT-5.6 Terra46.3
GPT-5.6 Luna44.7
Opus 4.742.8
Kimi K2.7 Code33.6
Composer 2.529.3
GLM-5.227.4
DeepSeek-V4-Pro20.0
MiniMax M316.6
Inkling15.9
Qwen3.7-Plus11.5
SWE-1.610.4
Loading Atlas data…