math benchmark
Multilingual MGSM (CoT)
Multilingual Grade School Math (MGSM) benchmark evaluates language models' chain-of-thought reasoning abilities across ten typologically diverse languages. Contains 250 grade-school math problems manually translated from GSM8K dataset into languages including Bengali and Swahili.
Updated Aug 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
Multilingual MGSM (CoT) leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 91.6% | 100.0% | 3 | C | |
| 2 | ME | 86.9% | 50.0% | 3 | C | |
| 3 | ME | 68.9% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
Multilingual MGSM (CoT) highlights
The top published results on this benchmark's own scale.
What is Multilingual MGSM (CoT)?
Definition and scoring fields from the benchmark registry.
Multilingual Grade School Math (MGSM) benchmark evaluates language models' chain-of-thought reasoning abilities across ten typologically diverse languages. Contains 250 grade-school math problems manually translated from GSM8K dataset into languages including Bengali and Swahili.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Multilingual MGSM (CoT)
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- multilingual-mgsm-(cot)|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about Multilingual MGSM (CoT).
Which model scores highest on Multilingual MGSM (CoT)?
Llama 3.1 405B Instruct is currently ranked first with 91.6%.
What does Multilingual MGSM (CoT) measure?
Multilingual Grade School Math (MGSM) benchmark evaluates language models' chain-of-thought reasoning abilities across ten typologically diverse languages. Contains 250 grade-school math problems manually translated from GSM8K dataset into languages including Bengali and Swahili.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 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.