ctxdexSynthetic model data for learning

Benchmark family

BIG-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.

KnowledgeGeneral reasoning

Definitions

Compare versions →

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

  1. BenchmarkBIG-Bench Extra Hard (BBEH)
    ActiveNewest in family
    Successor of BIG-Bench Hard (BBH)
    Scale
    4,520 examples
    Primary metric
    Accuracy
    Applicable models
    13
  2. BenchmarkBIG-Bench Hard (BBH)
    Active
    Scale
    23 tasks
    Primary metric
    Accuracy
    Applicable models
    13
  3. BenchmarkBIG-bench
    Active
    Scale
    Not recorded
    Primary metric
    Accuracy
    Applicable models
    0
Related outside this family
BIG-Bench Hard (BBH) — subset of — BIG-bench (family)

Family methodology

No family-level methodology recorded.

Across definitions

Tasks
BBEH reasoning task suite, BBH task suite
Sources
None recorded at family level
Last reviewed
2026-09-22

Applicability does not mean evaluated; benchmark result/model score data is outside this UI contract.