ctxdexSynthetic model data for learning

Benchmark family

LiveCodeBench

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 6 definitions is resolved separately.

Rolling evaluationCode generation

Definitions

Compare the newest 4 →

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

  1. BenchmarkLiveCodeBenchrelease_v6
    Active
    Successor of LiveCodeBench
    Scale
    1,055 problems
    Primary metric
    Pass@k
    Applicable models
    3
  2. BenchmarkLiveCodeBenchrelease_v5
    Active
    Successor of LiveCodeBench
    Scale
    880 problems
    Primary metric
    Pass@k
    Applicable models
    3
  3. BenchmarkLiveCodeBenchrelease_v4
    Active
    Successor of LiveCodeBench
    Scale
    713 problems
    Primary metric
    Pass@k
    Applicable models
    3
  4. BenchmarkLiveCodeBenchrelease_v3
    Active
    Successor of LiveCodeBench
    Scale
    612 problems
    Primary metric
    Pass@k
    Applicable models
    3
  5. BenchmarkLiveCodeBenchrelease_v2
    Active
    Successor of LiveCodeBench
    Scale
    511 problems
    Primary metric
    Pass@k
    Applicable models
    3
  6. BenchmarkLiveCodeBenchrelease_v1
    ActiveNewest in family
    Scale
    400 problems
    Primary metric
    Pass@k
    Applicable models
    3
Related outside this family
Ag-LiveCodeBench-X — derived from — LiveCodeBench

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
None recorded
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.