TydiQA
Multilingual
text
+
+
+
+
About
TyDiQA is a multilingual information-seeking question answering benchmark covering 11 typologically diverse languages with 200,000 question-answer pairs collected directly in each language without translation. This comprehensive evaluation tests AI models' ability to understand and answer questions across diverse linguistic structures, emphasizing realistic information-seeking scenarios and multilingual natural language understanding capabilities.
+
+
+
+
Evaluation Stats
Total Models2
Organizations1
Verified Results0
Self-Reported2
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
2 models
Top Score
31.7%
Average Score
31.6%
High Performers (80%+)
0Top Organizations
#1Meta
2 models
31.6%
+
+
+
+
Leaderboard
2 models ranked by performance on TydiQA
| License | Links | ||||
|---|---|---|---|---|---|
| Apr 5, 2025 | Llama 4 Community License Agreement | 31.7% | |||
| Apr 5, 2025 | Llama 4 Community License Agreement | 31.5% |
