MGSM
mathematicsPending Verification
Multilingual Grade School Math (MGSM) extends GSM8K to 10 languages.
Published: 2022
Score Range: 0-100
Top Score: 91.6
MGSM Leaderboard
| Rank | Model | Provider | Score | Parameters | Released | Type |
|---|---|---|---|---|---|---|
| 1 | Claude 3.5 Sonnet | Anthropic | 91.6 | 2024-06-20 | Multimodal | |
| 2 | Claude 3 Opus | Anthropic | 90.7 | 2024-03-04 | Multimodal | |
| 3 | GPT-4o | OpenAI | 90.5 | 2024-05-13 | Multimodal | |
| 4 | Claude 3.5 Haiku | Anthropic | 85.6 | 2024-10-22 | Multimodal | |
| 5 | Claude 3 Sonnet | Anthropic | 83.5 | 2024-03-04 | Multimodal | |
| 6 | DeepSeek-V3 | DeepSeek | 79.8 | 671B total, 37B activated | 2024-12-26 | Text |
| 7 | Claude 3 Haiku | Anthropic | 75.1 | 2024-03-04 | Multimodal |
About MGSM
Methodology
MGSM evaluates model performance using a standardized scoring methodology. Scores are reported on a scale of 0 to 100, where higher scores indicate better performance. For detailed information about the scoring system and methodology, please refer to the original paper.
Publication
This benchmark was published in 2022.Technical Paper