all the models — AI benchmark observatory
← Benchmarks

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.

id multilingual-mgsm-(cot) · max 1 · 3 models reported

#ModelScore
1Llama 3.1 405B Instruct
Meta · open
0.92
Multilingual MGSM (CoT) Leaderboard · all the models