UniClawBench: leaderboard

Metric: Pass rate (%; tasks reaching a final pass state, mean of the English and Chinese subsets) on 400 bilingual real-world tasks run live in Docker containers under the OpenClaw framework (v2026.3.11), with up to two simulated user follow-ups and a hidden GPT-5.4 Codex supervisor that grades step checkpoints. Source: arxiv.org. Saturation forecast: Around February 2027. 10 models tracked.

Top models

#ModelScore
1Claude Opus 4.847.5
2Claude Sonnet 4.645.5
3GPT-5.440.7
4Kimi K2.636.2
5Gemini 3.1 Pro (Preview)32.5
6Qwen 3.5 Plus31.8
7Gemini 3 Flash28.2
8GPT-5.4 Mini21.5
9Gemini 3.1 Flash Lite15.5
10GPT-4.115.2

Interactive version: theaggregate.ai/benchmark?slug=uniclawbench · How It Works · Data refreshed daily, snapshot 2026-09-29.