ClawArena (Claude Code): leaderboard
Metric: Composite Reliability Score (CRS, 0-100) on ClawArena (12 multi-turn scenarios, 337 evaluation rounds with staged updates; multi-choice and shell executable-check questions): the mean of the task completion rate and Robustness (success cohesion times failure dispersion), macro-averaged over scenarios; agent run in the Claude Code framework; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 66.31 |
| 2 | Claude Sonnet 4.6 | 62.16 |
| 3 | Claude Haiku 4.5 | 60.93 |
| 4 | Kimi K2.5 | 59.75 |
| 5 | GPT-5.1 | 47.57 |
| 6 | GPT-5.5 | 44.5 |
Interactive version: theaggregate.ai/benchmark?slug=clawarena-claude-code · How It Works · Data refreshed daily, snapshot 2026-10-07.