WebPageBench

What is WebPageBench?

An open framework for evaluating web agents, with 152 tasks across six instrumented mock sites, using event-log verification and controlled UI variants.

Released

2026-09-28

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.35026

WebPageBench paper

• Paper https://arxiv.org/abs/2609.35026

Which sources cite WebPageBench?

• WebPageBench

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench