MEGA XCOPA
Multilingual
text
+
+
+
+
About
MEGA XCopa is part of the MEGA (Multilingual Evaluation of Generative AI) benchmark suite, evaluating cross-lingual causal reasoning across 70 typologically diverse languages. It assesses language models' ability to determine plausible causes and effects in multilingual contexts, testing logical reasoning capabilities beyond English. The benchmark uses choice-of-plausible-alternatives format to evaluate causal inference across different language families and scripts.
+
+
+
+
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
76.6%
Average Score
69.8%
High Performers (80%+)
0Top Organizations
#1Microsoft
2 models
69.8%
+
+
+
+
Leaderboard
2 models ranked by performance on MEGA XCOPA
| License | Links | ||||
|---|---|---|---|---|---|
| Aug 23, 2024 | MIT | 76.6% | |||
| Aug 23, 2024 | MIT | 63.1% |
