bubench-run

Name: bubench-run
Availability: InStock
Author: LexMount

Execute and evaluate browser agent benchmark experiments across datasets and models.

19|5|Updated May 9, 2026

Search Tags:#automation #benchmarking #evaluation #performance-testing #browser-agents #lexbench

Ready to run

npx skills add https://github.com/lexmount/browseruse-agent-bench --skill bubench-run

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bubench-run
Source: https://github.com/lexmount/browseruse-agent-bench/tree/main/browseruse_bench/skills/bubench-run
Command: npx skills add https://github.com/lexmount/browseruse-agent-bench --skill bubench-run

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uv, and includes scripts (resource) components.

What problem does it solve?

This skill solves the complexity of managing long-running browser agent experiments, providing a structured way to execute, monitor, and evaluate agent performance across multiple datasets and models without manual oversight.

Core Features & Use Cases

Automated Pipeline Execution: Orchestrates the full lifecycle of agent runs and subsequent evaluations using background processes.
Performance Monitoring: Provides real-time tracking of agent progress, success rates, and error recovery using non-blocking log monitoring.
Incremental Evaluation: Efficiently handles large-scale benchmarks by skipping already-processed tasks, allowing for seamless multi-pass evaluation.

Quick Start

Use the bubench-run skill to execute a benchmark experiment for the browser-use agent using the deepseek model on the standard LexBench-Browser task set.

Frequently Asked Questions about bubench-run

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate browser agent benchmarking across multiple models?▼

To automate browser agent benchmarking, you can orchestrate the full lifecycle of agent runs and subsequent evaluations using background processes. This allows you to execute and monitor agent performance across multiple models without manual oversight.

What is non-blocking log monitoring for performance testing?▼

Non-blocking log monitoring for performance testing is a mechanism that provides real-time tracking of agent progress, success rates, and error recovery. It tracks automated performance metrics while long-running browser interactions execute in the background.

Do I need a local browser backend to run automated performance evaluations?▼

Yes, you need a local browser backend to run automated performance evaluations. The evaluation process requires integration with local browser backends and structured log analysis to execute browser interactions and ensure reproducible evaluation results.

Can I skip already-processed tasks during large-scale benchmark evaluation?▼

Yes, you can skip already-processed tasks during large-scale benchmark evaluation. The incremental evaluation feature efficiently handles large benchmarks by skipping processed tasks, allowing seamless multi-pass evaluation across diverse datasets.

Does uv work with browser agent benchmark experiments?▼

Yes, uv works with browser agent benchmark experiments as a required dependency. It supports the execution and evaluation of browser agent benchmark experiments across diverse datasets and model configurations.