Chatbot Arena (Text - Polish): leaderboard
arena.ai’s text leaderboard restricted to battles whose prompts are in Polish. 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. 232 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Fable 5.1 (Max) | 1510 | #10 (Claude Fable 5.1) |
| 2 | Claude Fable 5 (High) | 1510 | #20 (Claude Fable 5) |
| 3 | Gemini 3.5 Flash (High) | 1508 | #66 (Gemini 3.5 Flash) |
| 4 | Muse Spark 1.1 | 1507 | #55 |
| 5 | Gemini 3 Pro | 1505 | #82 |
| 6 | Claude Opus 5 (Max) | 1504 | #16 (Claude Opus 5) |
| 7 | Claude Opus 4.6 (High) | 1502 | #67 (Claude Opus 4.6) |
| 8 | Gemini 3.7 Flash (High) | 1502 | #24 (Gemini 3.7 Flash) |
| 9 | Claude Opus 5 (High) | 1502 | #16 (Claude Opus 5) |
| 10 | Claude Opus 4.7 | 1501 | #51 |
| 11 | GPT-5.6 Sol (xHigh) | 1501 | #22 (GPT-5.6 Sol) |
| 12 | Gemini 3 Flash | 1497 | #103 |
| 13 | Gemini 3.5 Flash (Medium) | 1496 | #66 (Gemini 3.5 Flash) |
| 14 | Claude Opus 4.6 | 1495 | #67 |
| 15 | Gemini 3.1 Pro (Preview) | 1494 | #64 |
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-text-polish · How It Works · Data refreshed daily, snapshot 2026-11-05.