Benchmark
MEGA MLQA Benchmark
What is MEGA MLQA?
MLQA as part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite. A multi-way aligned extractive QA evaluation benchmark for cross-lingual…
- Modality
- text
- Evaluates
- reasoning, language
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mega-mlqa?top_n=500
MEGA MLQA results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Phi-3.5-mini-instruct | Microsoft | 0.617 | 2024-08-23 | evidence |
| Phi-3.5-MoE-instruct | Microsoft | 0.653 | 2024-08-23 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.