WebTailBench
Live-web task definitions and rubrics for evaluating computer-use agents, with preserved original tasks, a refreshed V2 task suite and a separate refusal set.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Benchmarks
- Environment
- web
- Topics
- evaluation, web-navigation, safety-security
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T02:42:32Z
- Resource ID
- url:3b6dfd52f98bfe76bc7f
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- mit (publisher model/dataset card metadata; third-party assets retain their own terms)
- Document
- Not recorded
- Weights
- Not recorded
License review notes
- Data: The benchmark's Hub dataset card declares MIT in its metadata header (license: mit). Source 1
Evaluation protocol
- Focus
- live web task completion, unsafe-request refusal
- Setting
- interactive
- Observations
- web pages
- Actions / outputs
- browser interaction
- Evaluation
- Task-specific precomputed rubrics; refusal tasks are a separate evaluation population.
Scale and counting units
V2 refreshes task strings and rubrics while preserving V1 task IDs. Counts are task definitions, not independently verified runnable website states.
Compare source-reviewed profiles
Recorded specifications
- disabled
- false
- download url
- https://huggingface.co/datasets/microsoft/WebTailBench/tree/main
- gated
- false
- hub id
- microsoft/WebTailBench
Explore related topics
Scope and limitations
Public TSV files contain V1, V2 and refusal task definitions. The card declares MIT for the dataset. V1 and V2 share the same 609 task identities and must not be summed as distinct tasks. The May 2026 refresh supersedes calendar-bound task wording; live-site availability is not established by this metadata review.
Related resources
- documented by: Fara-7B: An Efficient Agentic Model for Computer Use
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-17T02:42:32Z. Supports: name, kind, summary, environments, topics, scope, relations, details, licenses.data.
Content fingerprint
c4cfc361d1d47d7855269af4110483363964e23f9c65244a1182830eccccbb7f - editorial primary review
Retrieved 2026-10-17T02:42:32Z. Supports: identity, release_status, details, licenses.data.
Content fingerprint
93469a20d333219dde89a225891a54ee716120d559eb8ac9f69a1a7ee84f57a3
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.