ClawArena (Claude Code) - Task Completion Rate: leaderboard
Metric: Task completion rate (%) on ClawArena (12 multi-turn scenarios, 337 evaluation rounds; per-round score macro-averaged over scenarios, multi-choice and executable checks); agent run in the Claude Code framework; higher is better. Source: arxiv.org. Saturation forecast: Around February 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 76.13 |
| 2 | Claude Sonnet 4.6 | 73.36 |
| 3 | Claude Haiku 4.5 | 72.29 |
| 4 | Kimi K2.5 | 66.77 |
| 5 | GPT-5.5 | 59.31 |
| 6 | GPT-5.1 | 55.19 |
Interactive version: theaggregate.ai/benchmark?slug=clawarena-claude-code-task-completion-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.