Domains: ScienceHumanitiesCoding
Skills: CodingAgenticMultimodalInstruction FollowingReasoning

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
5.5/10
Access Model: Public Prompts / Private Answers
"Quality Elo comes entirely from blind, pairwise preference votes cast by our recruited panel. In each comparison, a panelist sees two scenes built for the same task by two different models, interacts with both, and selects the one they prefer. Public votes cast in AA-3D Voting do not enter the rating calculation."
"Create an interactive adult man performing weightlifting exercises, with views that expose his muscles, skeleton and organs in anatomically accurate form."

Originality

Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"AA-3D v1.0 measures how well AI models build interactive 3D experiences. Each model receives a written brief and builds a single web page with three.js in an offline sandbox."

Freshness

Weight 20%
8/10
Initial Release: 2026-10Latest Refresh: 2026-10Rolling Updates: No
"Elo from blind pairwise votes · 95% confidence intervals · Higher is better · Data as at 12 October 2026"

Grading

Weight 15%
10/10
Integrity: Independent Offline (Leak-Verified)Sandbox: offline isolated
"We run every model in Stirrup, our open-source agent harness. Each task runs in its own sandbox with no network access."

Frontier Model Standings on AA-3D

Top 15 active models tracked
Rank Model Official Score Percentile
#1GPT-6.2 Astra max OpenAI1318 Elo100.0p
#2Claude Fable 5.2 max Anthropic1271 Elo98.8p
#3GPT-6.2 Sol max OpenAI1259 Elo95.0p
#4Claude Sonnet 5.5 max Anthropic1204 Elo91.1p
#5Claude Opus 5.5 max Anthropic1202 Elo87.2p
#6GPT-6 Astra max OpenAI1168 Elo83.3p
#7Gemini 4 Argon high Google1147 Elo79.4p
#8Claude Fable 5.1 max Anthropic1139 Elo75.6p
#9GPT-6 Sol max OpenAI1131 Elo71.7p
#10GPT-6.1 Sol max OpenAI1121 Elo67.8p
#11Kimi K3.1 Pro max Kimi1112 Elo64.0p
#12Muse Spark 1.3 max Meta1032 Elo60.1p
#13Inkling 2 Small default Thinking Machines1027 Elo56.3p
#14GPT-6 Luna max OpenAI1000 Elo52.4p
#15Claude Haiku 5.5 max Anthropic998 Elo48.5p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit AA-3D Tier A 7.8/10
[![BenchAudit Tier A](https://benchaudit.org/badges/aa-3d.svg)](https://benchaudit.org/benchmarks/aa-3d/)