Multimodal & Grounded benchmark
SimpleVQA leaderboard
Every model the catalog carries a published SimpleVQA value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureImage-grounded question answering
TasksVisual QA tasks
DifficultyGeneral visual understanding
Published byGLM-5V-Turbo
A visual question answering benchmark focused on straightforward image-grounded understanding.
SimpleVQA ranking
11 models with a published SimpleVQA value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Image-grounded question answering |
|---|---|---|---|
| 1 |  Qwen3.7 Plus | Alibaba | 81.7 |
| 2 |  Step 3.7 Flash | StepFun | 79.2 |
| 3 | Qwen3.8 Max | Alibaba | 75.0 |
| 4 | DSdots3-note Preview | Dots Studio | 72.5 |
| 5 |  Gemini 3.1 Pro | 72.4 | |
| 6 |  Muse Spark | Meta | 71.3 |
| 7 |  GPT-5.4 | OpenAI | 61.1 |
| 8 | Qwen3.6-35B-A3B | Alibaba | 58.9 |
| 9 |  Grok 4.20 | xAI | 57.4 |
| 10 | Qwen3.6-27B | Alibaba | 56.1 |
| 11 |  LFM2.5-VL-3B | LiquidAI | 35.4 |
Evidence key: Observed
Rows are ordered by the value GLM-5V-Turbo published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.