MEGA TyDi QA
Multilingual
text
+
+
+
+
About
MEGA TyDi QA is a multilingual question-answering benchmark within the MEGA evaluation suite, based on the Typologically Diverse QA dataset. This benchmark tests AI models' ability to answer questions across typologically diverse languages, evaluating cross-lingual transfer capabilities and multilingual comprehension in languages with varying grammatical structures and writing systems.
+
+
+
+
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
67.1%
Average Score
64.7%
High Performers (80%+)
0Top Organizations
#1Microsoft
2 models
64.7%
+
+
+
+
Leaderboard
2 models ranked by performance on MEGA TyDi QA
| License | Links | ||||
|---|---|---|---|---|---|
| Aug 23, 2024 | MIT | 67.1% | |||
| Aug 23, 2024 | MIT | 62.2% |
