Benchmark
MathVerse Benchmark
What is MathVerse?
MathVerse evaluates multimodal mathematical reasoning, testing whether models genuinely interpret visual math diagrams rather than relying on text.
- Released
- 2024-03-21
- Modality
- multimodal
- Evaluates
- math, multimodal, reasoning, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mathverse?top_n=500
MathVerse results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Seed 2.1 Pro | ByteDance | 0.897 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.892 | 2026-06-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.