Claw-Anything - Execution Score: leaderboard

Claw-Anything (2026) benchmarks always-on personal assistant agents in a simulated digital world with months of user activity, interdependent backend services and CLI and GUI devices, all run in the OpenHarness agent scaffold. This board is the average rubric score per task on a 0 to 1 scale, giving partial credit and weighting final outcomes; higher is better.

Metric: Average continuous execution score (0-1, the rubric soft score weighted toward final outcomes), over the 200 Claw-Anything tasks (simulated months of user activity, interdependent backend services, CLI Linux and GUI Android devices, reactive and proactive tasks), every model in the OpenHarness agent scaffold, three independent runs, rubric checks plus a Claude Sonnet 4.5 judge giving a pass label and a soft score; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.50.65#54
2Claude Opus 4.70.62#85
3Claude Sonnet 4.50.59#261
4GLM-5.10.59#198
5Qwen 3.6 27B0.58#351
6Kimi K2.60.57#192
7MiniMax-M2.70.52#539
8Qwen 3.5 27B0.5#375

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

Interactive version: theaggregate.ai/benchmark?slug=claw-anything-execution-score · How It Works · Data refreshed daily, snapshot 2026-11-21.