ClawArena — leaderboard
Metric: Composite Reliability Score. Source: www.clawarena.cc. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 68.28 |
| 2 | Gemma 4 31B | 63.8 |
| 3 | GPT-5.1 | 63.28 |
| 4 | GLM-5.1 | 60.63 |
| 5 | MiMo-V2.5-Pro | 59.65 |
| 6 | GPT-5.4 | 58.99 |
| 7 | Gemini 3.1 Pro (Preview) | 57.59 |
| 8 | Kimi K2.5 | 57.24 |
| 9 | Qwen 3.6 27B | 55.85 |
| 10 | DeepSeek V4 Pro | 55.25 |
| 11 | Qwen 3.6 Plus | 55.17 |
| 12 | GPT-5.2 | 54.18 |
| 13 | Qwen 3.6 35B A3B | 48.86 |
| 14 | GLM-4.7 Flash | 38.82 |
Interactive version: aibenchmarks.dev/benchmark?slug=clawarena · How the rankings work · Data refreshed daily, snapshot 2026-07-06.