language benchmark
MEGA XStoryCloze Leaderboard
MEGA XStoryCloze is a cross-lingual story completion task in the MEGA benchmark suite, using professionally translated versions of the English StoryCloze dataset in 10 non-English languages.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
MEGA XStoryCloze Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score82.80% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score73.50% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
MEGA XStoryCloze Highlights
The leading models and scores on this benchmark.
MEGA XStoryCloze Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for MEGA XStoryCloze
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is MEGA XStoryCloze?
What MEGA XStoryCloze measures and how its scores work.
It presents a four-sentence story and requires models to predict its correct ending.
It measures commonsense reasoning and narrative understanding using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MEGA XStoryCloze
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MEGA XStoryCloze.
Which model scores highest on MEGA XStoryCloze?
Phi-3.5-MoE-instruct is currently ranked first with 82.80%.
What are the top three models on MEGA XStoryCloze?
The current leaders are Phi-3.5-MoE-instruct (82.80%) and Phi-3.5-mini-instruct (73.50%).
Which MEGA XStoryCloze model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among MEGA XStoryCloze results?
The fastest matched records are Phi-3.5-mini-instruct (23.00 tok/s via Azure).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.