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

#ModelScore
1Claude Opus 4.776.13
2Claude Sonnet 4.673.36
3Claude Haiku 4.572.29
4Kimi K2.566.77
5GPT-5.559.31
6GPT-5.155.19

Interactive version: theaggregate.ai/benchmark?slug=clawarena-claude-code-task-completion-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.