multimodal benchmark
MMT-Bench
MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
MMT-Bench Ranking
Higher score ranks better on this benchmark.
| 1 | DE | 63.6% | 100.0% | 4 | C | |
| 2 | AC | 63.6% | 66.7% | 4 | C | |
| 3 | DE | 62.9% | 33.3% | 4 | C | |
| 4 | DE | 53.2% | 0.0% | 4 | C |
MMT-Bench Score Distribution
A closer view of the leading scores on this benchmark.
MMT-Bench Highlights
The leading models and scores on this benchmark.
What is MMT-Bench?
What MMT-Bench measures and how its scores work.
MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MMT-Bench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mmt-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MMT-Bench.
Which model scores highest on MMT-Bench?
DeepSeek VL2 is currently ranked first with 63.6%.
What does MMT-Bench measure?
MMT-Bench is a comprehensive multimodal benchmark for evaluating Large Vision-Language Models towards multitask AGI. It comprises 31,325 meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering 32 core meta-tasks and 162 subtasks in multimodal understanding.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.