AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
MathVision
MATH-Vision is a dataset designed to measure multimodal mathematical reasoning capabilities. It focuses on evaluating how well models can solve mathematical problems that require both visual understanding and mathematical reasoning, bridging the gap between visual and mathematical domains.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- The Chinese University of Hong Kong
- Benchmark release
- 2024-02-22
- Collected
- 2026-08-17
- Modality
- multimodal
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 33
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Kimi K3 | 0.978 | Not recorded | Not recorded | 2026-07-16 · model_announcement | LLM Stats |
| Qwen3.8-27B | 0.946 | Not recorded | Not recorded | 2026-08-14 · model_announcement | LLM Stats |
| Seed 2.1 Pro | 0.945 | Not recorded | Not recorded | 2026-06-24 · model_announcement | LLM Stats |
| Kimi K2.6 | 0.932 | Not recorded | Not recorded | 2026-04-20 · model_announcement | LLM Stats |
| Seed 2.1 Turbo | 0.927 | Not recorded | Not recorded | 2026-06-24 · model_announcement | LLM Stats |
| Qwen3.7-Plus | 0.903 | Not recorded | Not recorded | 2026-05-31 · model_announcement | LLM Stats |
| Qwen3.6 Plus | 0.88 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.862 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.86 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Gemma 4 31B | 0.856 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Kimi K2.5 | 0.842 | Not recorded | Not recorded | 2026-01-27 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.839 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Gemma 4 26B-A4B | 0.824 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Gemma 4 12B | 0.797 | Not recorded | Not recorded | 2026-05-23 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Thinking | 0.746 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Step3-VL-10B | 0.708 | Not recorded | Not recorded | 2026-01-15 · model_announcement | LLM Stats |
| DiffusionGemma 26B-A4B | 0.705 | Not recorded | Not recorded | 2026-06-10 · model_announcement | LLM Stats |
| Qwen3 VL 32B Thinking | 0.702 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Instruct | 0.665 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Thinking | 0.657 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Instruct | 0.634 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Thinking | 0.627 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Instruct | 0.602 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 4B Thinking | 0.6 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Gemma 4 E4B | 0.595 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Qwen3 VL 8B Instruct | 0.539 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Gemma 4 E2B | 0.524 | Not recorded | Not recorded | 2026-04-02 · model_announcement | LLM Stats |
| Qwen3 VL 4B Instruct | 0.516 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2.5 VL 32B Instruct | 0.384 | Not recorded | Not recorded | 2025-02-28 · model_announcement | LLM Stats |
| Qwen2.5 VL 72B Instruct | 0.381 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| QvQ-72B-Preview | 0.359 | Not recorded | Not recorded | 2024-12-25 · model_announcement | LLM Stats |
| Qwen2.5 VL 7B Instruct | 0.2507 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Qwen2.5-Omni-7B | 0.25 | Not recorded | Not recorded | 2025-03-27 · model_announcement | LLM Stats |