ctxdexSynthetic model data for learning

Benchmark family

Programbench

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.

Software Engineering

Definitions

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

  1. BenchmarkProgramBench
    ActiveNewest in family
    Scale
    200 tasks
    Primary metric
    Resolved Rate
    Applicable models
    6
Related outside this family
ProgramBench — related to — SWE-bench

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
Black Box Program Reimplementation
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.