ctxdexSynthetic model data for learning

Benchmark family

AgentBench

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.

Function CallingHeterogeneous InteractionTool UseGeneral Agent

Definitions

Compare versions →

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

  1. BenchmarkAgentBench FC
    ActiveNewest in family
    Derived from AgentBench (original / v0.2 protocol)
    Scale
    5 environments
    Primary metric
    Task Success Rate
    Applicable models
    51
  2. BenchmarkAgentBench (original / v0.2 protocol)v0.2 protocol
    Historical
    Scale
    269 cases
    Primary metric
    Task Success Rate
    Applicable models
    51

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
Heterogeneous Interactive Agent Execution, Stateful Multi Turn Tool Use, Tool Selection And Invocation
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.