nottelabs/open-operator-evals

Opensource benchmark evaluating web operators/agents performance

29
/ 100
Experimental

This project helps evaluate how well different web agents or 'operators' perform common online tasks, such as booking travel or finding information on websites. It takes various web agents as input and produces a detailed performance report, including success rates, completion times, and reliability metrics. Anyone developing, deploying, or deciding on which web automation agent to use can utilize this to objectively compare their effectiveness.

No commits in the last 6 months.

Use this if you need to compare the real-world performance of different web automation agents or evaluate how well your own agent navigates and completes tasks on various websites.

Not ideal if you are looking for a tool to build or train web agents, as this project focuses solely on benchmarking existing ones.

web-automation agent-evaluation performance-benchmarking AI-testing operations-efficiency
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

47

Forks

7

Language

Python

License

Last pushed

Apr 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/nottelabs/open-operator-evals"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.