Confirm Action

Are you sure you want to proceed?

Release planning · no model scores

OpenHands frontend evidence mapping

Exact V3 collection, facet, metric, lineage, identity and rights mapping for OpenHands frontend from OpenHands Index.

V3 evidence records

1 collection mapping

A repeated upstream benchmark can map to several collections. Each record below preserves its own task role, facets, capability atoms, subject identity, metrics, lineages and exclusions.

primary evidence · frontend-web/openhands-index/openhands-frontend

Frontend, UI & Web Apps

Which models are best at frontend, UI, and web-app creation?

Upstream access
machine-ready
Eligibility
runnable-now
Registry
registered
Max task directness
80%

Collection facets

  • Functional implementation · objective · 25%

    Implement required behaviours and state correctly.

  • Responsive accessibility · hybrid · 25%

    Work across viewports, keyboard use, semantics, and contrast.

  • Visual hierarchy · hybrid · 25%

    Create coherent layout, typography, spacing, and emphasis.

  • Brief fidelity and polish · hybrid · 25%

    Reflect supplied product facts and finish the details that make the page usable.

Capability atoms

frontend_task_completion

Subject identity

Declared:
agent
Metric partitions:
harnessed-model
Separate partition required:
yes
Identity projection:
forbidden

Usable evidence lineages

  • swe-bench-multimodal/harnessed-model

Exact metric contract

MetricLineageSubjectProtocolUse
category.frontendOpenHands Index — Frontendswe-bench-multimodalharnessed-modelOpenHands Index 2026.06.30 / SWE-Bench Multimodalusable

Exclusions and blockers

  • metric subject identity differs from the editorial mapping; publish and calibrate each identity partition separately

Mapping note

Attribute to the exact OpenHands configuration.