language benchmark
TydiQA Leaderboard
TydiQA is a multilingual question answering benchmark covering 11 typologically diverse languages with 204K question-answer pairs collected directly in each language without translation.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
TydiQA Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score31.70% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelME | Score31.50% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
TydiQA Highlights
The leading models and scores on this benchmark.
TydiQA Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for TydiQA
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is TydiQA?
What TydiQA measures and how its scores work.
TydiQA is a language benchmark consisting of questions written by people seeking genuine information across 11 typologically diverse languages.
It measures question-answering performance using Score, reported as a ratio, and tests model generalization across diverse linguistic structures.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TydiQA
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TydiQA.
Which model scores highest on TydiQA?
Llama 4 Maverick is currently ranked first with 31.70%.
What are the top three models on TydiQA?
The current leaders are Llama 4 Maverick (31.70%) and Llama 4 Scout (31.50%).
Which TydiQA model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among TydiQA results?
The fastest matched records are Llama 4 Scout (776.10 tok/s via Groq) and Llama 4 Maverick (307.30 tok/s via Groq).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.