Atlas

Benchmarks

Visual Cipher Bench

Visual Cipher Bench (Einsia.AI, Navers Lab and Tsinghua University) gives coding agents 40 puzzles presented only as images, run in Harbor with a 60-minute limit and no network access; GPT models run in Codex CLI and the others in Claude Code. The score is accuracy over three runs of every puzzle (120 attempts). Most models score at or near zero, so it is shown as a diagnostic outside the capability fit.

Models
6
Top score
26.7
Leader
GPT-6 Astra
Updated
Nov 12, 2026
Resolution
—
Saturation
—

No signal or difficulty estimate. Held out of the fit by design.

Organizations
6 dated models · 1 frontier modelsClosed weightsOpen weights
Data: Einsia.AIatlas.village.dev

Visual Cipher Bench leaderboard

Loading Atlas data…