PawBench

About PawBench

🐾 PawBench English · 简体中文 A Model × Harness co-evaluation benchmark for agentic AI. 150 agent tasks · 9 models · 3 harnesses · task slices · diagnostic traces The same model can behave very differently once it is placed inside a real agent runtime. A failure may come from model reasoning, missing tools, weak skill discovery, poor workspace awareness, brittle web access, or a completion check that is too loose. A single final pass rate cannot separate these causes. PawBench is built around one c

Quick Facts

Compatible Skills

These tools work well together with PawBench for enhanced workflows:

• OpenClawProBench — semantic(0.72)+same_lang+similar_pop+shared_platform (60%)
• a11y-llm-eval — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)
• ollama-benchmark — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (58%)
• llm-d-benchmark — semantic(0.37)+complementary+same_lang+similar_pop+shared_platform (58%)

More Codex Skill Tools

Explore other popular codex skill tools:

• openclaw ⭐ 382.2k
• hermes-agent ⭐ 211.4k
• ui-ux-pro-max-skill ⭐ 101.6k
• graphify ⭐ 80.2k
• graphify ⭐ 77.1k
• open-design ⭐ 76.2k
• agent-skills ⭐ 71.4k
• career-ops ⭐ 59.1k
• taste-skill ⭐ 56.5k
• system_prompts_leaks ⭐ 53.8k

Popular Python Agent Tools

• hermes-agent ⭐ 211.4k · Codex Skill
• AutoGPT ⭐ 185.4k · Agent Tool
• skills ⭐ 157.3k · Claude Skill
• langflow ⭐ 151.4k · Agent Tool
• open-webui ⭐ 143.9k · MCP Server

Frequently Asked Questions