Open Multilingual Reasoning (13B) - MNumGLUESub: leaderboard
The "MNumGLUESub" subtask of Open Multilingual Reasoning (13B). Open Multilingual Reasoning leaderboard — multilingual math-reasoning accuracy of open ~13B models across MGSM, MSVAMP and MNumGLUE subsets.
Metric: Accuracy (%). Source: huggingface.co. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-3.5 Turbo | 49.4 | #865 |
Interactive version: theaggregate.ai/benchmark?slug=open-multilingual-reasoning-13b-mnumgluesub · How It Works · Data refreshed daily, snapshot 2026-10-20.