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 - Hermes — leaderboard

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

Top models

#ModelScore
1Claude Opus 4.678.44
2Qwen 3.7 Max72.29
3DeepSeek V4 Pro72.06
4Qwen 3.6 Plus70.41
5Qwen 3.6 27B68.2
6Qwen 3.6 Max Preview68.09
7Kimi K2.666.36
8GLM-5.163.19
9Qwen 3.6 35B A3B56.74

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