Benchmark
DynaMath
A multimodal mathematics and reasoning benchmark focused on dynamic visual problem solving.
- Modality
- multimodal
- Categories
- math, multimodal, reasoning, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 7
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.5-122B-A10B | Qwen | 0.859 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.877 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.85 | 2026-02-24 | evidence |
| Qwen3.6 Plus | Qwen | 0.88 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.856 | 2026-04-21 | evidence |
| Seed 2.1 Pro | ByteDance | 0.731 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.681 | 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.