Claude Skill

pinchbench/skill

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Built by the team at kilo.ai.

Overview

Stars1,260
Forks144
LanguagePython
Last pushed2026-07-02
Last synced2026-07-03
View on GitHub

Repository

Ownerpinchbench
Repositoryskill
Full namepinchbench/skill
Repo ID1,154,980,232

Install this Skill

git clone https://github.com/pinchbench/skill.git

Registry

Typeopenclaw_skill
Quality score80/100
Verificationreadme_parsed
Last verified2026-06-03
Platforms
ClaudeOpenClaw
Capabilities
pdfmemorysearchvideoterminal
Detected files
README.mdSKILL.mdpyproject.tomltests
Config keys
PINCHBENCH_OFFICIAL_KEYKEYOPENROUTER_API_KEYKILO_API_KEYANTHROPIC_API_KEYOPENAI_API_KEY

Summary

PinchBench is a benchmarking system designed to evaluate LLM models as OpenClaw coding agents, built by the team at kilo.ai.

Chinese description

PinchBench是一个用于评估LLM模型作为OpenClaw编码代理的基准测试系统。由https://kilo.ai的人类团队用🦀制作。

Key features

  • Evaluates LLM models as coding agents
  • OpenClaw-based benchmarking framework
  • Built by the team at kilo.ai
  • Python-based implementation

Use cases

  • Benchmarking LLM coding agent performance
  • Comparing different LLM models for coding tasks
  • Research on agent-based code generation

README excerpt

# 🦀 PinchBench **Real-world benchmarks for AI coding agents** [![Leaderboard](https://img.shields.io/badge/leaderboard-pinchbench.com-blue)](https://pinchbench.com) [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE) <!-- task-count-badge -->![Tasks](https://img.shields.io/badge/tasks-53-orange)<!-- /task-count-badge --> > **Note:** This repository contains the benchmark skill/tasks. It is NOT the source of official leaderboard results. To add models to the official results, modify [pinchbench/scripts/default-models.yml](https://github.com/pinchbench/scripts/blob/main/default-models.yml). PinchBench measures how well LLM models perform as the brain of an [OpenClaw](https://github.com/openclaw/openclaw) agent. Instead of synthetic tests, we throw real tasks at agents: scheduling meetings, writing code, triaging email, researching topics, and managing files. Results are collected on a public leaderboard at **[pinchbench.com](https://pinchbench.com)**. ![PinchBench](pinchbench.png) ## Why PinchBench? Most LLM benchmarks test isolated capabilities. PinchBench tests what actually matters for coding agents: - **Tool usage** — Can the model call the right tools with the right parameters? - **Multi-step reasoning** — Can it chain together actions to complete complex tasks? - **Real-world messiness** — Can it handle ambiguous instructions and incomplete information? - **Practical outcomes** — Did it actually create the file, send the email, or schedule the meeting? ## Quick Start ```bash # Clone the skill git clone https://github.com/pinchbench/skill.git cd skill # Run benchmarks with your model of choice ./scripts/run.sh --model openrouter/anthropic/claude-sonnet-4 # Or run specific tasks ./scripts/run.sh --model openrouter/openai/gpt-4o --suite t

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-07-03