reasoning benchmark
MEGA XCOPA
XCOPA (Cross-lingual Choice of Plausible Alternatives) as part of the MEGA benchmark suite. A typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, including resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. Requires models to select which choice is the effect or cause of a given premise.
Updated Aug 7, 2026
Published models2
Registry coverage2
MetricScore
EvidenceB
MEGA XCOPA leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | MI | 76.6% | 100.0% | 2 | C | |
| 2 | MI | 63.1% | 0.0% | 2 | C |
Score distribution
Top published rows on the benchmark's original scale.
MEGA XCOPA highlights
The top published results on this benchmark's own scale.
What is MEGA XCOPA?
Definition and scoring fields from the benchmark registry.
XCOPA (Cross-lingual Choice of Plausible Alternatives) as part of the MEGA benchmark suite. A typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, including resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. Requires models to select which choice is the effect or cause of a given premise.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MEGA XCOPA
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mega-xcopa|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about MEGA XCOPA.
Which model scores highest on MEGA XCOPA?
Phi-3.5-MoE-instruct is currently ranked first with 76.6%.
What does MEGA XCOPA measure?
XCOPA (Cross-lingual Choice of Plausible Alternatives) as part of the MEGA benchmark suite. A typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, including resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. Requires models to select which choice is the effect or cause of a given premise.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.