Pinchbench

PinchBench Benchmark Skill

PinchBench measures how well LLM models perform as the brain of an OpenClaw agent. Results are collected on a public leaderboard at pinchbench.com.

Prerequisites

• Python 3.10+
• uv package manager
• OpenClaw instance (this agent)

Quick Start

cd 

# Run benchmark with a specific model
uv run benchmark.py --model anthropic/claude-sonnet-4

# Run only automated tasks (faster)
uv run benchmark.py --model anthropic/claude-sonnet-4 --suite automated-only

# Run specific tasks
uv run benchmark.py --model anthropic/claude-sonnet-4 --suite task_calendar,task_stock

# Skip uploading results
uv run benchmark.py --model anthropic/claude-sonnet-4 --no-upload

Available Tasks (23)

| Task | Category | Description | |------|----------|-------------| | task_sanity | Basic | Verify agent works | | task_calendar | Productivity | Calendar event creation | | task_stock | Research | Stock price lookup | | task_blog | Writing | Blog post creation | | task_weather | Coding | Weather script | | task_summary | Analysis | Document summarization | | task_events | Research | Conference research | | task_email | Writing | Email drafting | | task_memory | Memory | Context retrieval | | task_files | Files | File structure creation | | task_workflow | Integration | Multi-step API workflow | | task_clawdhub | Skills | ClawHub interaction | | task_skill_search | Skills | Skill discovery | | task_image_gen | Creative | Image generation | | task_humanizer | Writing | Text humanization | | task_daily_summary | Productivity | Daily digest | | task_email_triage | Email | Inbox triage | | task_email_search | Email | Email search | | task_market_research | Research | Market analysis | | task_spreadsheet_summary | Analysis | Spreadsheet analysis | | task_eli5_pdf_summary | Analysis | PDF simplification | | task_openclaw_comprehension | Knowledge | OpenClaw docs comprehension | | task_second_brain | Memory | Knowledge management |

Command Line Options

| Option | Description | |--------|-------------| | --model | Model identifier (e.g., anthropic/claude-sonnet-4) | | --suite | all, automated-only, or comma-separated task IDs | | --output-dir | Results directory (default: results/) | | --timeout-multiplier | Scale task timeouts for slower models | | --runs | Number of runs per task for averaging | | --no-upload | Skip uploading to leaderboard | | --register | Request new API token for submissions | | --upload FILE | Upload previous results JSON |

Token Registration

To submit results to the leaderboard:

# Register for an API token (one-time)
uv run benchmark.py --register

# Run benchmark (auto-uploads with token)
uv run benchmark.py --model anthropic/claude-sonnet-4

Results

Results are saved as JSON in the output directory:

# View task scores
jq '.tasks[] | {task_id, score: .grading.mean}' results/0001_anthropic-claude-sonnet-4.json

# Show failed tasks
jq '.tasks[] | select(.grading.mean < 0.5)' results/*.json

# Calculate overall score
jq '{average: ([.tasks[].grading.mean] | add / length)}' results/*.json

Adding Custom Tasks

Create a markdown file in tasks/ following TASK_TEMPLATE.md. Each task needs:

• YAML frontmatter (id, name, category, grading_type, timeout)
• Prompt section
• Expected behavior
• Grading criteria
• Automated checks (Python grading function)

Leaderboard

View results at pinchbench.com. The leaderboard shows:

• Model rankings by overall score
• Per-task breakdowns
• Historical performance trends

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: pinchbench
• Source: pinchbench/skill
• License: MIT
• Homepage: https://pinchbench.com

Install and usage instructions live in the source repository linked above.