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.
Phi-3.5-MoE-instruct from Microsoft currently leads the MEGA XCOPA leaderboard with a score of 0.766 across 2 evaluated AI models.
What MEGA XCOPA measures
MEGA XCOPA is a text benchmark that evaluates large language models on language and reasoning tasks. LLM Stats tracks 2 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.7, with the leader reaching 0.8.
Compare leaders on the best AI for language and best AI for reasoning leaderboards.
Publication
- Paper
- XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
- Authors
- Edoardo Maria Ponti, Goran Glavaš, Olga Majewska, Qianchu Liu, and 2 others
- Published
- arXiv
- 2005.00333
Abstract
In order to simulate human language capacity, natural language processing systems must be able to reason about the dynamics of everyday situations, including their possible causes and effects. Moreover, they should be able to generalise the acquired world knowledge to new languages, modulo cultural differences. Advances in machine reasoning and cross-lingual transfer depend on the availability of challenging evaluation benchmarks. Motivated by both demands, we introduce Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, which includes resource-poor languages like Eastern Apurímac Quechua and Haitian Creole. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods based on multilingual pretraining and zero-shot fine-tuning falls short compared to translation-based transfer. Finally, we propose strategies to adapt multilingual models to out-of-sample resource-lean languages where only a small corpus or a bilingual dictionary is available, and report substantial improvements over the random baseline. The XCOPA dataset is freely available at github.com/cambridgeltl/xcopa.
Phi-3.5-MoE-instruct leads with 76.6%, followed by Phi-3.5-mini-instruct at 63.1%.
Progress Over Time
Interactive timeline showing model performance evolution on MEGA XCOPA
MEGA XCOPA Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Microsoft | 60B | — | — | ||
| 2 | Microsoft | 4B | — | — |
FAQ
Common questions about MEGA XCOPA.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions