Atlas

Benchmarks

Frontier3DBench L2 scenes

Einsia

Level 2 of Frontier3DBench: 65 tasks that build a Blender scene from a brief, a rendered image or a real photograph, or edit an existing scene to match a reference, scored on 0 to 100.

Models
8
Top score
70.3
Leader
GPT-6.1 Sol
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 · 5 frontier modelsClosed weightsOpen weights
Data: Einsia.AIatlas.village.dev
#ModelSettingScoreSource
1GPT-6.1 Solmax · Codex
70.3
Frontier3DBench leaderboard: GPT-6.1 Sol
2Claude Opus 5.5max · Claude Code
62.6
Frontier3DBench leaderboard: Claude Opus 5.5
3GPT-6 Astramax · Codex
62.5
Frontier3DBench leaderboard: GPT-6 Astra
4MiniMax M3.1 Flashmax · Claude Code
60.5
Frontier3DBench leaderboard: MiniMax M3.1 Flash
5Kimi K3.1 Promax · Kimi CLI
59.4
Frontier3DBench leaderboard: Kimi K3.1 Pro
6GLM-5.3 Flashmax · ZCode
55.9
Frontier3DBench leaderboard: GLM-5.3-Flash
7Kimi K3max · Kimi CLI
55.5
Frontier3DBench leaderboard: Kimi K3
8GPT-6 Lunamax · Codex
54.1
Frontier3DBench leaderboard: GPT-6 Luna
Loading Atlas data…