Multimodal · Benchmark profile
A visual question answering benchmark focused on straightforward image-grounded understanding.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on SimpleVQA
Qwen3.7-Plus leads at 81.7%, followed by Step 3.7 Flash (79.2%) and Gemini 3.1 Pro (72.4%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
8 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Qwen3.7-Plus | #1 | Alibaba Cloud | 81.7% |
| Step 3.7 Flash | #2 | StepFun | 79.2% |
| Gemini 3.1 Pro | #3 | 72.4% | |
| Muse Spark | #4 | Meta | 71.3% |
| GPT-5.4 | #5 | OpenAI | 61.1% |
| Qwen3.6-35B-A3B | #6 | Alibaba Cloud | 58.9% |
| Grok 4.20 | #7 | xAI | 57.4% |
| Qwen3.6 27B | #8 | Alibaba Cloud | 56.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 81.7% |
| #2 | Step 3.7 Flash step-3-7-flash | StepFun | open | Estimated reference | 79.2% |
| #3 | Gemini 3.1 Pro gemini-3-1-pro | closed | Estimated reference | 72.4% | |
| #4 | Muse Spark muse-spark | Meta | closed | Reference only | 71.3% |
| #5 | GPT-5.4 gpt-5.4 | OpenAI | closed | Reference only | 61.1% |
| #6 | Qwen3.6-35B-A3B qwen3-6-35b-a3b | Alibaba Cloud | open | Estimated reference | 58.9% |
| #7 | Grok 4.20 grok-4.20 | xAI | closed | Estimated reference | 57.4% |
| #8 | Qwen3.6 27B qwen3.6-27b | Alibaba Cloud | open | Estimated reference | 56.1% |
The top of this snapshot is led by Qwen3.7-Plus at 81.7%; third place is 9.3 points behind. The top-8 spread is 25.6 points.
About SimpleVQA
A visual question answering benchmark focused on straightforward image-grounded understanding. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A visual question answering benchmark focused on straightforward image-grounded understanding.
Qwen3.7-Plus by Alibaba Cloud currently leads with 81.7%.
8 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
