reasoning benchmark
TydiQA
A multilingual question answering benchmark covering 11 typologically diverse languages with 204K question-answer pairs. Questions are written by people seeking genuine information and data is collected directly in each language without translation to test model generalization across diverse linguistic structures.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
TydiQA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 31.7% | 100.0% | 2 | C | |
| 2 | ME | 31.5% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
TydiQA highlights
The top published results on this benchmark's own scale.
What is TydiQA?
Definition and scoring fields from the benchmark registry.
A multilingual question answering benchmark covering 11 typologically diverse languages with 204K question-answer pairs. Questions are written by people seeking genuine information and data is collected directly in each language without translation to test model generalization across diverse linguistic structures.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- TydiQA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- tydiqa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about TydiQA.
Which model scores highest on TydiQA?
Llama 4 Maverick is currently ranked first with 31.7%.
What does TydiQA measure?
A multilingual question answering benchmark covering 11 typologically diverse languages with 204K question-answer pairs. Questions are written by people seeking genuine information and data is collected directly in each language without translation to test model generalization across diverse linguistic structures.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.