Atlas

Benchmarks

Frontier3DBench L3 open worlds

Einsia

Level 3 of Frontier3DBench: 15 tasks that build an interactive Unreal Engine open world from a text brief or images, with runtime tests of its behavior, scored on 0 to 100.

Models
8
Top score
61.3
Leader
GPT-6 Astra
Updated
Nov 6, 2026
Resolution
—
Saturation
—
Signal
83rdpercentile
205 benchmarks from 0.8 to 3.6219 benchmarks from 3.6 to 6.4134 benchmarks from 6.4 to 9.393 benchmarks from 9.3 to 12.155 benchmarks from 12.1 to 14.925 benchmarks from 14.9 to 17.713 benchmarks from 17.7 to 20.55 benchmarks from 20.5 to 23.37 benchmarks from 23.3 to 26.27 benchmarks from 26.2 to 29.01 benchmark from 29.0 to 31.83 benchmarks from 31.8 to 34.66 benchmarks from 34.6 to 37.43 benchmarks from 37.4 to 40.21 benchmark from 40.2 to 43.11 benchmark from 45.9 to 48.71 benchmark from 65.6 to 68.4

134th strongest of 779

Signal-to-noise +11.88 for the Frontier3DBench family

Difficulty
Not estimated

Another benchmark represents this family in the fit.

8 dated models · 2 frontier modelsClosed weightsOpen weights
Data: Einsia.AIatlas.village.dev
#ModelSettingScoreSource
1GPT-6 Astramax · Codex
61.3
Frontier3DBench leaderboard: GPT-6 Astra
2GPT-6.1 Solmax · Codex
58.9
Frontier3DBench leaderboard: GPT-6.1 Sol
3Claude Opus 5.5max · Claude Code
58.2
Frontier3DBench leaderboard: Claude Opus 5.5
4Kimi K3.1 Promax · Kimi CLI
49.3
Frontier3DBench leaderboard: Kimi K3.1 Pro
5Kimi K3max · Kimi CLI
42.0
Frontier3DBench leaderboard: Kimi K3
6MiniMax M3.1 Flashmax · Claude Code
41.7
Frontier3DBench leaderboard: MiniMax M3.1 Flash
7GPT-6 Lunamax · Codex
38.5
Frontier3DBench leaderboard: GPT-6 Luna
8GLM-5.3 Flashmax · ZCode
35.1
Frontier3DBench leaderboard: GLM-5.3-Flash
Loading Atlas data…