ctxdexSynthetic model data for learning

Benchmark family

Swe Bench Live

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 5 definitions is resolved separately.

Software Engineering

Definitions

Compare the newest 4 →

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

  1. BenchmarkSWE-bench-Live
    ActiveNewest in family
    Scale
    1,888 counts
    Primary metric
    Resolved Rate
    Applicable models
    6
  2. BenchmarkSWE-bench-Live Lite
    Active
    Subset of SWE-bench-Live
    Scale
    300 tasks
    Primary metric
    Resolved Rate
    Applicable models
    6
  3. BenchmarkSWE-bench-Live Verified
    Active
    Subset of SWE-bench-Live
    Scale
    500 tasks
    Primary metric
    Resolved Rate
    Applicable models
    6
  4. BenchmarkSWE-bench-Live/MultiLang
    Active
    Derived from SWE-bench-Live
    Scale
    431 repositorys
    Primary metric
    Resolved Rate
    Applicable models
    6
  5. BenchmarkSWE-bench-Live/Windows
    Active
    Derived from SWE-bench-Live
    Scale
    9 languages
    Primary metric
    Resolved Rate
    Applicable models
    6
Related outside this family
OS-bench — derived from — SWE-bench-Live
SWE-bench-Live — derived from — SWE-bench

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
Issue Resolution
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.