Atlas

Benchmarks

Frontier3DBench

Einsia

Frontier3DBench (Navers Lab, Einsia.AI and Tsinghua University) tests coding agents on building editable 3D projects from text, images or briefs: objects and scenes in Blender, and interactive open worlds in Unreal Engine. Each submission is rendered, inspected and run, then scored for visual fidelity, structural consistency and task fulfillment. Its 145 tasks span 9 categories, and Total weights objects 30%, scenes 30% and open worlds 40%. Each model runs in its developer's harness, or in Claude Code where it has none, at its highest available effort.

Models
8
Top score
66.0
Leader
GPT-6.1 Sol
Updated
Nov 6, 2026
Resolution
~2 mo
Sharp
Saturation
~Aug 2028
Projected
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

Difficulty
67thpercentile
1 benchmark from 5.9 to 14.81 benchmark from 23.6 to 32.52 benchmarks from 32.5 to 41.31 benchmark from 41.3 to 50.22 benchmarks from 50.2 to 59.08 benchmarks from 59.0 to 67.97 benchmarks from 67.9 to 76.819 benchmarks from 76.8 to 85.623 benchmarks from 85.6 to 94.541 benchmarks from 94.5 to 103.331 benchmarks from 103.3 to 112.239 benchmarks from 112.2 to 121.148 benchmarks from 121.1 to 129.973 benchmarks from 129.9 to 138.859 benchmarks from 138.8 to 147.6118 benchmarks from 147.6 to 156.5127 benchmarks from 156.5 to 165.3113 benchmarks from 165.3 to 174.235 benchmarks from 174.2 to 183.117 benchmarks from 183.1 to 191.99 benchmarks from 191.9 to 200.81 benchmark from 200.8 to 209.64 benchmarks from 209.6 to 218.5

253rd hardest of 779

Capability needed 159.8

8 dated models · 3 frontier modelsClosed weightsOpen weights
Data: Einsia.AIatlas.village.dev
#ModelSettingScoreSource
1GPT-6.1 Solmax · Codex
66.0
Frontier3DBench leaderboard: GPT-6.1 Sol
2GPT-6 Astramax · Codex
63.9
Frontier3DBench leaderboard: GPT-6 Astra
3Claude Opus 5.5max · Claude Code
62.3
Frontier3DBench leaderboard: Claude Opus 5.5
4Kimi K3.1 Promax · Kimi CLI
56.0
Frontier3DBench leaderboard: Kimi K3.1 Pro
5MiniMax M3.1 Flashmax · Claude Code
52.5
Frontier3DBench leaderboard: MiniMax M3.1 Flash
6Kimi K3max · Kimi CLI
49.2
Frontier3DBench leaderboard: Kimi K3
7GPT-6 Lunamax · Codex
48.6
Frontier3DBench leaderboard: GPT-6 Luna
8GLM-5.3 Flashmax · ZCode
47.6
Frontier3DBench leaderboard: GLM-5.3-Flash
Loading Atlas data…