Benchmarks

WebTestBench

An end-to-end web-testing benchmark where agents derive test checklists from development instructions, interact with deployed applications and report functional or constraint-related defects.

AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.

Original source ↗Read as MarkdownRecord JSON

What is this resource?

Resource type
Benchmarks
Environment
web
Topics
evaluation, web-navigation, tool-integration
Record publication date
Not recorded
Evidence retrieved
2026-10-17T11:18:18Z
Resource ID
github:friedrichor/webtestbench

What licenses are recorded?

Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.

Code
Apache-2.0 (Repository source LICENSE; external tools and services retain their own licenses.)
Data
apache-2.0 (Publisher Hub-card license declaration for the released benchmark dataset.)
Document
Not recorded
Weights
Not recorded

License review notes

Evaluation protocol

Focus
web functionality testing, latent permission and business constraints
Setting
interactive
Observations
web application interface, development instruction
Actions / outputs
browser interaction, test checklist generation, defect reports
Evaluation
The supplied WebTester pipeline separates checklist generation from interactive defect detection and provides a scoring workflow.

Scale and counting units

The 100 archive files are not counted as 100 independent test tasks or defects. Backend/tool versions and deployment settings affect reproducibility.

Compare source-reviewed profiles

Recorded specifications

availability
Public evaluation harness and ungated web-application archive manifest.
repository revision
04873065bdb0938ed53d809559d4ab473c7ccd31

Explore related topics

EvaluationWeb navigationTool integration

Scope and limitations

Public evaluation/deployment scripts accompany an ungated Hub release with JSON/JSONL metadata and 100 application ZIP files. The ZIP count is an artifact inventory, not an asserted test-case or defect count. The documented baseline uses Claude Agent SDK and a pinned Playwright MCP version with external model credentials; these were not installed or run. Code and data Apache-2.0 declarations are retained separately.

Related resources

Primary evidence and verification

Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.

  1. editorial primary review

    Retrieved 2026-10-17T11:18:18Z. Supports: name, kind, summary, environments, topics, scope, notes, relations, details.benchmark_protocol.

    Content fingerprintb41472026cd7d4f81a01d58bf39193dc1fabc7875c61e370090a20cc77500cdd
  2. editorial primary review

    Retrieved 2026-10-17T11:18:18Z. Supports: identity.

    Content fingerprint7203ecc2aae5f1697eeeb804ca8f21d47b9f22a8b8fa43a4064c4e1c49f5e72c
  3. editorial primary review

    Retrieved 2026-10-17T11:22:55Z. Supports: release_status, details.repository_revision.

    Content fingerprintbd1f09149b00d59a0078d414216bd2fb78e09ce7212d15bbda84ddec7052c8af
  4. editorial primary review

    Retrieved 2026-10-17T11:23:08Z. Supports: identity, release_status, details.benchmark_protocol.

    Content fingerprintdb1e97f40107038ae03835dc20f17b13b37e74b5c8587f8c39b441271618f017
  5. editorial primary review

    Retrieved 2026-10-17T11:23:08Z. Supports: licenses.data, details.benchmark_protocol.

    Content fingerprint6f2f94a25ed66a14779f6b4e6686044d0510eb32a0187645cc473978d93f7c5b
  6. editorial primary review

    Retrieved 2026-10-17T11:22:55Z. Supports: licenses.code.

    Content fingerprintc71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4

Suggest a correction

Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.