ctxdexSynthetic model data for learning

Benchmark family

WorkArena

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 2 definitions is resolved separately.

AgenticKnowledge WorkWeb AgentWeb browser

Definitions

Compare versions →

Newest first, following the recorded successor chain. Each definition is resolved against models separately.

  1. BenchmarkWorkArena L1L1
    ActiveNewest in family
    Scale
    33 tasks
    Primary metric
    Task Success Rate
    Applicable models
    51
  2. BenchmarkWorkArena++++
    Active
    Derived from WorkArena L1
    Scale
    341 tasks
    Primary metric
    Task Success Rate
    Applicable models
    51

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
Web Navigation, Web State Modification, Infeasibility Handling
Sources
None recorded at family level
Last reviewed
2026-09-23

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.