DeepTumorVQA - Recognition: leaderboard
DeepTumorVQA (2026) is a hierarchical visual question answering benchmark on abdominal 3D CT that follows the evidence chain of tumor diagnosis, scored as multiple-choice accuracy on a balanced 10,000-question test subset. This board is accuracy in percent on the binary recognition questions such as lesion presence or organ enlargement, answered directly from the image input without tools; higher is better.
Metric: Accuracy (%) on the Recognition-stage questions (binary: lesion presence, organ enlargement; chance 50%) of the balanced 10,000-question multiple-choice test subset of DeepTumorVQA (42 subtypes over abdominal 3D CT volumes), direct inference zero-shot with each model's native input (2D organ-centred slices for 2D models, the full 3D volume for 3D models); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 9B | 58.4 | #828 |
| 2 | Qwen 3 VL 4B | 56.6 | #1151 |
| 3 | Qwen 3.5 35B A3B | 53 | #492 |
| 4 | InternVL3-8B | 52.5 | #1782 |
| 5 | Meissa-4B | 51.5 | |
| 6 | LLaVA-OneVision-7B | 51.3 | #2981 |
| 7 | Qwen 3 VL 8B | 50.7 | #917 |
| 8 | HuatuoGPT-Vision-7B | 50.1 | #2162 |
| 9 | LLaVA-Med | 50 | |
| 10 | MedGemma 1.5 4B | 48.3 | #2716 |
| 11 | Gemini 3 Flash | 42.6 | #175 |
| 12 | RadFM | 39.1 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=deeptumorvqa-recognition · How It Works · Data refreshed daily, snapshot 2026-11-21.