Benchmark family

TruthfulQA

A family groups the versions of one benchmark. It is not evaluated and has no applicable models of its own; each of its 2 definitions is resolved separately.

FactualityTruthfulness

Definitions

Compare versions →

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

BenchmarkTruthfulQA
ActiveNewest in family
Scale
817 questions
Primary metric
Truthful Rate
Applicable models
30
BenchmarkTruthfulQA Improved Multiple Choice2025-01
Active
Variant of TruthfulQA
Scale
Not recorded
Primary metric
Accuracy
Applicable models
30

Family methodology

No family-level methodology recorded.

Across definitions

Tasks: None recorded
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.