Confirm Action

Are you sure you want to proceed?

Release planning · no model scores

GDPval-AA v2 evidence mapping

Exact V3 collection, facet, metric, lineage, identity and rights mapping for GDPval-AA v2 from Artificial Analysis.

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 · strategy-knowledge-work/artificial-analysis/gdpval-aa-v2

Professional Knowledge Work & Strategy

Which models are best at professional knowledge work and strategy?

Upstream access
machine-ready
Eligibility
runnable-now
Registry
registered
Max task directness
65%

Collection facets

  • Decision memos · hybrid · 25%

    Frame the decision, surface trade-offs, and recommend a defensible course.

  • Prioritisation · hybrid · 25%

    Rank competing initiatives with explicit criteria and opportunity cost.

  • Scenario planning · hybrid · 25%

    Reason under uncertainty without inventing facts or false precision.

  • Implementation plans · hybrid · 25%

    Translate strategy into owners, dependencies, milestones, and risks.

Capability atoms

professional_deliverable_qualitydecision_quality

Subject identity

Declared:
harnessed-model
Metric partitions:
harnessed-model
Separate partition required:
no
Identity projection:
forbidden

Usable evidence lineages

  • gdpval-aa/harnessed-model

Exact metric contract

MetricLineageSubjectProtocolUse
gdpval_aa_normalizedGDPval-AA Normalizedgdpval-aaharnessed-modelGDPval-AA v2 via the Stirrup agent harnessusable

Exclusions and blockers

  • source redistribution is conditional: assumed

Mapping note

Stirrup-harnessed professional work; exact configuration identity is required.