MathVista what it measures, how it is scored and who leads it
Multimodal · UCLA, University of Washington and Microsoft · introduced Oct 3, 2023 · Accuracy
About this benchmark
- Task
- Solve math problems set in images: plots, tables, geometry, puzzles.
- Dataset
- 6,141 examples from 28 existing multimodal datasets and 3 new ones.
- Method
- Answers extracted and compared with the reference.
- Metric
- Accuracy
- Organization
- UCLA, University of Washington and Microsoft
- Introduced
- Oct 3, 2023
- Official leaderboard
- mathvista.github.io/
Versions
Newest first. New versions are added, never rewritten.
| Version | Date | |
|---|---|---|
| 1Released with the paper. | Oct 3, 20232 years ago | Released with the paper. |
Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.