Atlas

Benchmarks

← All benchmarks

FeatureArc (whole-feature chain gate)

Code · 2026-10-27

73 manually reviewed feature-evolution tasks from Tencent's Hunyuan team, mined from the histories of 53 repositories in Python, TypeScript, Rust and Go. Each task is a chain of 2 to 10 dependent stages (263 in all) that extend one user-visible feature. A coding agent receives each stage's requirements document and interface contract in turn, in one persistent session and workspace, with a four-hour stage budget and no hidden-test feedback or rollback between stages. The score is the share of tasks whose chain-level fail-to-pass and pass-to-pass suites both pass on the final workspace, in percent.

Top models (higher is better)

ModelScore
Claude Opus 5.549.3
GPT-6 Astra37.0
GLM-5.331.5
Grok 4.726.0
Gemini 3.8 Flash23.3
Kimi K319.2
DeepSeek V4 Pro 081317.8
Loading Atlas data…