MMT-Bench
InternVL3.5-241B-A28B 72.7% Only in system cards Vision-language models answer 31,325 multiple-choice questions across many multimodal tasks such as recognition, localization, reasoning and planning.
ICML 2024.
In the authors’ words
Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench 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. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving 30 LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
InternVL3.5-241B-A28B leads with 72.7%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 InternVL3.5-241B-A28B 72.7%
- 2
Nemotron Nano 12B v2 VL 63.8%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | InternVL3.5-241B-A28B | 72.7% | Aug 2025 | Model card | |
| 2 | Nemotron Nano 12B v2 VL | 63.8% | Nov 2025 | Model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 6 Nov 2025 | Nemotron Nano 12B v2 VL technical report | 63.8 | MMT-Bench (Val), reasoning on (Table 3). Reasoning off 65.5 | Capabilities |
| 25 Aug 2025 | InternVL3.5-241B-A28B technical report | 72.7 | MMT (val) (Table 5) | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy.
Qwen 3.8 Max 97.7% - ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%