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 - QwenPaw — leaderboard

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

Top models

#ModelScore
1Qwen 3.6 Max Preview78.35
2Claude Opus 4.678.27
3Qwen 3.7 Max77.65
4DeepSeek V4 Pro75.64
5Qwen 3.6 Plus75.01
6Qwen 3.6 27B72.66
7GLM-5.171.07
8Qwen 3.6 35B A3B68.28
9Kimi K2.666.59

Interactive version: aibenchmarks.dev/benchmark?slug=pawbench-qwenpaw · 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.