Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Metrics
LLM Benchmark Hub
Loading data...

PawBench - OpenClaw — leaderboard

Metric: Overall Score (%). Source: agentscope-ai.github.io. 9 models tracked.

Top models

#ModelScore
1Claude Opus 4.676.11
2DeepSeek V4 Pro75.39
3Qwen 3.6 Max Preview75.11
4Qwen 3.6 Plus73.57
5Qwen 3.6 27B72.94
6Qwen 3.7 Max72.5
7GLM-5.168.49
8Qwen 3.6 35B A3B67.79
9Kimi K2.666.56

Interactive version: aibenchmarks.dev/benchmark?slug=pawbench-openclaw · How the rankings work · Data refreshed daily, snapshot 2026-07-19.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.