TyDi QA
by Clark et al. / Google Research · open-source · Last verified 2026-03-17
TyDi QA (Typologically Diverse Question Answering) is a multilingual QA benchmark covering 11 typologically diverse languages from different language families. Unlike benchmarks translated from English, questions are natively authored by speakers of each language, providing genuine linguistic diversity.
https://ai.google.com/research/tydiqa ↗B
B—Above Average
Adoption: B+Quality: AFreshness: BCitations: B+Engagement: F
Specifications
- License
- Apache-2.0
- Pricing
- open-source
- Capabilities
- evaluation, multilingual-qa, reading-comprehension
- Integrations
- Use Cases
- model-evaluation, multilingual-nlp, qa-systems
- API Available
- No
- Evaluated Models
- gpt-4o, multilingual-bert, xlm-roberta-large, gemini-2-5-pro
- Metrics
- f1-score, exact-match
- Methodology
- Gold passage task: model selects answer span from a provided Wikipedia passage. Goldp F1 and EM averaged across 11 languages. Primary task is span extraction; secondary task is answer presence detection (boolean).
- Last Run
- 2025-12-20
- Tags
- question-answering, multilingual, typologically-diverse, reading-comprehension
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
66.1Adoption
72
Quality
89
Freshness
67
Citations
78
Engagement
0