language benchmark
MLQA as part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite. A multi-way aligned extractive QA evaluation benchmark for cross-lingual question answering across 7 languages (English, Arabic, German, Spanish, Hindi, Vietnamese, and Simplified Chinese) with over 12K QA instances in English and 5K in each other language.
Updated Aug 11, 2026
Higher score ranks better on this benchmark.
| 01 | MI | 65.3% | 100.0% | 2 | C | |
| 02 | MI | 61.7% | 0.0% | 2 | C |
A closer view of the leading scores on this benchmark.
The leading models and scores on this benchmark.
What MEGA MLQA measures and how its scores work.
MLQA as part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite. A multi-way aligned extractive QA evaluation benchmark for cross-lingual question answering across 7 languages (English, Arabic, German, Spanish, Hindi, Vietnamese, and Simplified Chinese) with over 12K QA instances in English and 5K in each other language.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about MEGA MLQA.
Phi-3.5-MoE-instruct is currently ranked first with 65.3%.
MLQA as part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite. A multi-way aligned extractive QA evaluation benchmark for cross-lingual question answering across 7 languages (English, Arabic, German, Spanish, Hindi, Vietnamese, and Simplified Chinese) with over 12K QA instances in English and 5K in each other language.
Yes. Higher values rank better for this benchmark.
2 model results are currently shown.
No. This benchmark is shown for reference but does not contribute to the overall score.