Skip to main content
Evaluation sources/AutomationBench-AA
ParticipatingProfessional work

AutomationBench-AA

Artificial Analysis · Public model evaluation results from AutomationBench-AA.

Official evaluation
Source description

This source measures concrete delivery performance in Professional work; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Gemini 4 Carbon0.7781660675.42026-11-11
Gemini 4 Argon0.7751346975.22026-11-05
Claude Fable 5.20.7642233874.62026-11-10
MiniMax M3.1 Flash0.725218172.52026-11-05
Claude Sonnet 5.50.7176882172.12026-11-05
Muse Wonder Full0.713307571.82026-10-18
Muse Wonder Full0.713307571.82026-10-17
Muse Wonder Full0.713307571.82026-11-05
Claude Opus 5.50.6953868170.92026-11-05
DeepSeek V4.1 Flash0.6889097870.52026-11-05
DeepSeek V4.1 Flash0.6849296570.32026-11-05
GPT-6 Astra0.6849174870.32026-11-05
Muse Wonder0.6809455170.12026-10-18
Muse Wonder0.6809455170.12026-11-05
Muse Wonder0.6809455170.12026-10-17
Ling-3.1-flash0.6754660769.82026-11-05
Grok 4.60.6699736869.52026-11-05
DeepSeek V4.1 Flash0.6664095469.32026-10-31
GPT-6.1 Sol0.6657372169.32026-11-05
Grok 4.70.6555835168.72026-11-05
MiMo V2.6 Flash0.6405168367.92026-10-18
MiMo V2.6 Flash0.6405168367.92026-11-05
MiMo V2.6 Flash0.6405168367.92026-10-17
GLM 5.30.6220286566.92026-11-05

Page 1 of 5

Frequently asked questions