ClawArena (PicoClaw) - Task Completion Rate: leaderboard

ClawArena (2026) tests agents as persistent assistants in evolving information environments: 12 multi-turn scenarios with conflicting sources, staged updates and implicit preferences, checked by multiple-choice and executable shell questions, here with the agent run inside the PicoClaw agent framework. Task completion rate in percent; higher is better.

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 PicoClaw framework; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.577.15#54
2GPT-5.171.51#240
3Kimi K2.565.58#266

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=clawarena-picoclaw-task-completion-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.