Atlas

Benchmarks

← All benchmarks

CUA-bench — SUPERHOT

Agents · 2026-09-18

Ordered-milestone progress on SUPERHOT within three hours.

Top models (higher is better)

ModelScore
GPT-6 Astra20.0
Claude Fable 5.112.0
GPT-5.6 Sol8.0
Claude Opus 54.0
Gemini 3.8 Flash0.0
Loading Atlas data…