Chatbot Arena (Text - Expert): leaderboard
arena.ai’s text leaderboard restricted to battles whose prompts arena.ai tags as expert-level: the small share of hard prompts that need deep professional or academic expertise. It is the 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. 364 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5 (High) | 1550 | #20 (Claude Fable 5) |
| 2 | Claude Opus 4.6 (High) | 1547 | #67 (Claude Opus 4.6) |
| 3 | Claude Sonnet 5.5 (xHigh) | 1546 | #14 (Claude Sonnet 5.5) |
| 4 | Gemini 4 Argon (High) | 1543 | #9 (Gemini 4 Argon) |
| 5 | Claude Opus 5 (High) | 1541 | #16 (Claude Opus 5) |
| 6 | Claude Opus 5.5 (High) | 1536 | #3 (Claude Opus 5.5) |
| 7 | Claude Opus 4.6 | 1534 | #67 |
| 8 | Claude Opus 4.7 | 1534 | #51 |
| 9 | GPT-6.1 Sol (Max) | 1534 | #7 (GPT-6.1 Sol) |
| 10 | Claude Opus 4.7 (High) | 1534 | #51 (Claude Opus 4.7) |
| 11 | Kimi K3 (Max) | 1533 | #35 (Kimi K3) |
| 12 | GPT-5.6 Sol (xHigh) | 1533 | #22 (GPT-5.6 Sol) |
| 13 | MiMo-V2.6-Pro | 1531 | #48 |
| 14 | Claude Opus 5 (Max) | 1530 | #16 (Claude Opus 5) |
| 15 | Muse Spark 1.3 (Max) | 1528 | #31 (Muse Spark 1.3) |
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-text-expert · How It Works · Data refreshed daily, snapshot 2026-11-05.