Chatbot Arena (Code): leaderboard
Human preference votes on real-world coding tasks including code generation, debugging, and explanation, using Elo ratings from blind pairwise comparisons by developers.
Metric: Elo. Source: arena.ai. Source: benchmarklist.com. Saturation forecast: Around December 2027. 142 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 1813 | #3 (Claude Opus 5.5) |
| 2 | GPT-6 Astra (Max) | 1786 | #6 (GPT-6 Astra) |
| 3 | Claude Sonnet 5.5 (xHigh) | 1774 | #11 (Claude Sonnet 5.5) |
| 4 | GPT-6.1 Sol (Max) | 1755 | #7 (GPT-6.1 Sol) |
| 5 | Claude Fable 5.1 (Max) | 1744 | #9 (Claude Fable 5.1) |
| 6 | Claude Sonnet 5.5 (High) | 1715 | #11 (Claude Sonnet 5.5) |
| 7 | Claude Opus 5 (Max) | 1691 | #12 (Claude Opus 5) |
| 8 | GPT-6 Sol (Max) | 1688 | #14 (GPT-6 Sol) |
| 9 | Gemini 4 Argon (High) | 1678 | #8 (Gemini 4 Argon) |
| 10 | Qwen 3.8 Max (0902) | 1674 | #29 |
| 11 | Qwen 3.8 Max | 1672 | #35 |
| 12 | Claude Opus 5 (High) | 1657 | #12 (Claude Opus 5) |
| 13 | Muse Spark 1.3 (Max) | 1657 | #24 (Muse Spark 1.3) |
| 14 | Kimi K3 (Max) | 1654 | #30 (Kimi K3) |
| 15 | Grok 4.7 (xHigh) | 1639 | #25 (Grok 4.7) |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=chatbot-arena-code · How It Works · Data refreshed daily, snapshot 2026-10-20.