Chatbot Arena (Text - Life, Physical & Social Science): leaderboard

arena.ai’s text leaderboard restricted to battles whose prompts arena.ai’s occupational classifier assigns to life, physical and social science work. Same crowd-vote Arena Score as the headline board, refitted over that category’s votes alone, so the ordering can differ from the overall table and the error bars are wider.

Metric: Arena Score. Source: arena.ai. 412 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 4 Argon (High)1541#9 (Gemini 4 Argon)
2Claude Opus 4.6 (High)1528#67 (Claude Opus 4.6)
3Claude Opus 4.7 (High)1526#51 (Claude Opus 4.7)
4Claude Fable 5 (High)1525#20 (Claude Fable 5)
5Kimi K3 (Max)1521#35 (Kimi K3)
6Claude Opus 4.61519#67
7Gemini 3.8 Flash (High)1519#30 (Gemini 3.8 Flash)
8Claude Fable 5.1 (Max)1519#10 (Claude Fable 5.1)
9Claude Opus 5.5 (High)1518#3 (Claude Opus 5.5)
10Muse Spark 1.2 (xHigh)1517#69 (Muse Spark 1.2)
11Qwen 3.8 Max1515#34
12Claude Opus 4.71514#51
13Gemini 3.7 Flash (High)1513#24 (Gemini 3.7 Flash)
14Muse Spark 1.3 (Max)1513#31 (Muse Spark 1.3)
15Claude Opus 5 (Max)1512#16 (Claude Opus 5)

Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-text-life-physical-social-science · How It Works · Data refreshed daily, snapshot 2026-11-05.