Chatbot Arena (Vision - Entity Recognition): leaderboard

Metric: Arena Score. Source: arena.ai. 46 models tracked.

Top models

#ModelScore
1Gemini 3 Pro1298
2Gemini 3 Flash1289
3Gemini 3.1 Pro (Preview)1283
4Gemini 3.1 Flash Lite (Preview)1272
5GPT-5 (High)1260
6Claude Opus 4.6 (High)1258
7Gemini 2.5 Pro1252
8Grok 4.20 Beta (0309) (Reasoning)1244
9Grok 41239
10GPT-5.1 (High)1238
11O3 (2025-04-16)1232
12Claude Opus 4.7 (High)1229
13Kimi K2.5 (Thinking)1228
14Qwen 3.5 397B A17B1226
15Grok 4.20 Multi-Agent1226

Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-vision-entity-recognition · How It Works · Data refreshed daily, snapshot 2026-09-05.