Chatbot Arena (Vision - Entity Recognition): leaderboard

arena.ai’s vision leaderboard restricted to battles that ask what or who is in the image. Same crowd-vote Arena Score as the headline vision board, refitted over that category’s votes alone.

Metric: Arena Score. Source: arena.ai. 51 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro1290#80
2Gemini 3 Flash1289#99
3Gemini 3.1 Pro (Preview)1283#58
4Gemini 3.1 Flash Lite (Preview)1270#194
5GPT-5 (High)1261#98 (GPT-5)
6Gemini 2.5 Pro1251#152
7Claude Opus 4.7 (High)1241#49 (Claude Opus 4.7)
8GPT-5.2 Instant1238#210
9Claude Opus 4.61237#63
10Grok 4.20 Beta (0309) (Reasoning)1237#204 (Grok 4.20 Beta (0309))
11Grok 41236#181
12Claude Opus 4.6 (High)1234#63 (Claude Opus 4.6)
13O3 (2025-04-16)1231#121
14Kimi K2.5 (Thinking)1231#144 (Kimi K2.5)
15GPT-5.1 (High)1231#135 (GPT-5.1)

Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-vision-entity-recognition · How It Works · Data refreshed daily, snapshot 2026-10-20.