MGSM
MGSM (Multilingual Grade School Math) is a benchmark of grade-school math problems. Contains 250 grade-school math problems manually translated from the GSM8K dataset into ten typologically diverse languages: Spanish, French, German, Russian, Chinese, Japanese, Thai, Swahili, Bengali, and Telugu. Evaluates multilingual mathematical reasoning capabilities.
Llama 4 Maverick from Meta currently leads the MGSM leaderboard with a score of 0.923 across 31 evaluated AI models.
Llama 4 Maverick leads with 92.3%, followed by 
o3-mini at 92.0% and 
Claude 3.5 Sonnet at 91.6%.
Progress Over Time
Interactive timeline showing model performance evolution on MGSM
MGSM Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Meta | 400B | — | — | ||
| 2 | OpenAI | — | — | — | ||
| 3 | Anthropic | — | — | — | ||
| 3 | Anthropic | — | — | — | ||
| 5 | 70B | — | — | |||
| 6 | OpenAI | — | — | — | ||
| 7 | Anthropic | — | — | — | ||
| 8 | Meta | 109B | — | — | ||
| 9 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 10 | OpenAI | — | — | — | ||
| 11 | OpenAI | — | 128K | $10.00 / $30.00 | ||
| 12 |  Google | — | — | — | ||
| 13 | OpenAI | — | — | — | ||
| 14 | 90B | — | — | |||
| 15 | Anthropic | — | — | — | ||
| 16 |  Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 17 | Anthropic | — | — | — | ||
| 18 | Google | — | — | — | ||
| 19 |  Microsoft | 15B | — | — | ||
| 20 | Anthropic | — | — | — | ||
| 21 | OpenAI | — | — | — | ||
| 22 | 11B | — | — | |||
| 23 | Google | 8B | — | — | ||
| 24 | Microsoft | 4B | — | — | ||
| 25 | 2B | — | — | |||
| 26 | Microsoft | 60B | — | — | ||
| 27 | 3B | — | — | |||
| 28 | OpenAI | — | 16K | $0.50 / $1.50 | ||
| 29 | 2B | — | — | |||
| 29 | Google | 8B | — | — | ||
| 31 | Microsoft | 4B | — | — |
FAQ
Common questions about MGSM.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions