A visual question-answering benchmark focused on the factual accuracy of short natural-language answers from multimodal models.
Browse the latest scores, model modes, release dates, and parameter sizes for SimpleVQA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Step 3.7 Flash Thinking EnabledTools | 79.20 | 2026-05-29 | 198B | Free Commercial | |
Step3 Standard Mode | 62.20 | 2025-07-31 | 321B | Free Commercial | |
 Qwen3.5-27B Thinking Enabled | 56.00 | 2026-02-25 | 27B | Free Commercial |
