A multilingual benchmark that translates 250 grade school math problems from GSM8K into 10 typologically diverse languages: Bengali, German, Spanish, French, Japanese, Russian, Swahili, Telugu, Thai, and Chinese.
As of June 2, 2026, DeepSeek V4 Flash Base leads the MGSM leaderboard with 85.7% , followed by DeepSeek V4 Pro Base (84.4%).
DeepSeek V4 Flash Base
DeepSeek
DeepSeek V4 Pro Base
DeepSeek
Year
2022
Tasks
250 problems × 11 languages
Format
Math word problems
Difficulty
Grade school math, multilingual
MGSM evaluates mathematical reasoning across languages, revealing that performance can vary significantly across languages, with lower-resource languages (Bengali, Swahili, Telugu) typically showing the largest gaps.
Version
MGSM 2022
Refresh cadence
Static
Staleness state
Stale
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A multilingual benchmark that translates 250 grade school math problems from GSM8K into 10 typologically diverse languages: Bengali, German, Spanish, French, Japanese, Russian, Swahili, Telugu, Thai, and Chinese.
DeepSeek V4 Flash Base by DeepSeek currently leads with a score of 85.7% on MGSM.
2 AI models have been evaluated on MGSM on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.