Chatbot Arena (Text - Longer Query): leaderboard
The arena.ai text board restricted to battles whose prompt runs past 500 tokens, the fixed cut given in the site's category post. Each battle is one prompt answered by two anonymous models, with the voter choosing the better reply. The Bradley-Terry rating is refit over this subset alone, and higher is better.
Metric: Arena Score. Source: arena.ai. 392 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 4 Argon (High) | 1545 | #8 (Gemini 4 Argon) |
| 2 | Claude Opus 4.6 (High) | 1524 | #63 (Claude Opus 4.6) |
| 3 | Claude Opus 5.5 (High) | 1524 | #3 (Claude Opus 5.5) |
| 4 | Claude Fable 5 (High) | 1521 | #16 (Claude Fable 5) |
| 5 | Claude Opus 4.6 | 1517 | #63 |
| 6 | Claude Opus 4.7 (High) | 1515 | #49 (Claude Opus 4.7) |
| 7 | Gemini 3.8 Flash (High) | 1510 | #21 (Gemini 3.8 Flash) |
| 8 | Claude Fable 5.1 (Max) | 1509 | #9 (Claude Fable 5.1) |
| 9 | Claude Opus 4.7 | 1508 | #49 |
| 10 | Kimi K3 (Max) | 1504 | #30 (Kimi K3) |
| 11 | Claude Opus 5 (High) | 1504 | #12 (Claude Opus 5) |
| 12 | Claude Opus 4.8 (High) | 1503 | #37 (Claude Opus 4.8) |
| 13 | Claude Sonnet 5.5 (xHigh) | 1503 | #11 (Claude Sonnet 5.5) |
| 14 | Gemini 3.1 Pro (Preview) | 1500 | #58 |
| 15 | Claude Opus 5 (Max) | 1500 | #12 (Claude Opus 5) |
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-text-longer-query · How It Works · Data refreshed daily, snapshot 2026-10-20.