Atlas

Benchmarks

← All benchmarks

CL-Bench Database Exploration Gain

Agents · 2026-05-04

Mean cumulative gain over the stateless baseline across 40 sequential instances of the CL-Bench database exploration task.

Top models (higher is better)

ModelScore
Sonnet 4.613.9
GPT-5.412.9
Gemini 3 Flash Preview11.5
Opus 4.79.6
Gemini 3.1 Pro Preview6.8
Loading Atlas data…