Skip to main content
Evaluation sources/Arena Agent Overall
ObservingProfessional work

Arena Agent Overall

LMArena · Public model evaluation results from Arena Agent Overall.

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

Claude Opus 5.50.1995562589689.92026-11-08
Gemini 4 Carbon0.16630613029183.32026-11-08
Claude Sonnet 5.50.15994371740582.02026-11-08
Claude Fable 5.10.14335182914478.72026-11-08
GPT-6 Astra0.14238994554778.52026-11-08
GPT-6.1 Sol0.12527511889875.12026-11-08
GPT-6.1 Terra0.12102900587874.22026-11-08
Gemini 4 Argon0.10828589688471.72026-11-08
Muse Wonder Full0.09086749938968.22026-11-08
Claude Fable 50.07700479395165.42026-11-08
Claude Opus 50.07495110951665.02026-11-08
Claude Opus 4.80.07131379676664.32026-10-08
GPT-6 Sol0.07004553975264.02026-11-08
Muse Wonder0.04935621874659.92026-10-16
Muse Wonder0.04935621874659.92026-10-16
GPT-5.6 Sol0.04526173575859.12026-11-08
GPT-5.50.03120313955956.22026-10-20
Grok 4.70.02649939540555.32026-11-08
MiMo V2.6 Flash0.02598333419755.22026-10-16
MiMo V2.6 Flash0.02598333419755.22026-10-16
Gemini 3.8 Flash0.02383796830454.82026-11-08
MiMo V2.6 Pro0.02332197326254.72026-11-08
Muse Spark 1.30.02213243062754.42026-11-08
Claude Sonnet 50.02061236025954.12026-11-08

Page 1 of 3

Frequently asked questions