Atlas

Benchmarks

← All benchmarks

Build-A-Chip-Bench Functional Pass

Agents · 2026-10-14

Share of all Build-A-Chip-Bench tasks whose final design passes functional verification against the hidden verification IP. It is one of the two pass/fail gates inside the headline score, so it is kept as a diagnostic and never enters capability.

Top models (higher is better)

ModelScore
GPT-6 Astra85.0
Claude Fable 5.165.0
Kimi K325.0
Gemini 3.8 Flash20.0
GLM-5.315.0
Loading Atlas data…