ctxdexSynthetic model data for learning

Benchmark family

Terminal-Bench-Science

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 1 definition is resolved separately.

AgenticTerminal AgentTerminal

Definitions

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

  1. BenchmarkTerminal-Bench-Science 0.10.1
    ActiveNewest in family
    Scale
    70 tasks
    Primary metric
    Accuracy
    Applicable models
    51
Related outside this family
Terminal-Bench-Science 0.1 — related to — Terminal-Bench 4.0

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
Terminal Use
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.