ctxdexSynthetic model data for learning

Benchmark family

Multi Swe Bench

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 3 definitions is resolved separately.

MultilingualSoftware Engineering

Definitions

Compare versions →

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

  1. BenchmarkMulti-SWE-bench
    ActiveNewest in family
    Scale
    2,132 tasks
    Primary metric
    Resolved Rate
    Applicable models
    6
  2. BenchmarkMulti-SWE-bench Flash
    Active
    Subset of Multi-SWE-bench
    Scale
    300 tasks
    Primary metric
    Resolved Rate
    Applicable models
    6
  3. BenchmarkMulti-SWE-bench Mini
    Active
    Subset of Multi-SWE-bench
    Scale
    50 languages
    Primary metric
    Resolved Rate
    Applicable models
    6
Related outside this family
Kotlin Benchmark — First Public Iteration — related to — Multi-SWE-bench
Multi-SWE-bench — derived from — SWE-bench
Multi-SWE-bench — related to — SWE-bench Multilingual
Multi-SWE-bench — related to — SWE-PolyBench

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.