DeepTumorVQA - Measurement: 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 four-option measurement questions on volumes, Hounsfield units and ratios, answered directly from the image input without tools; higher is better.

Metric: Accuracy (%) on the Measurement-stage questions (four numeric options: organ and lesion volume, Hounsfield units, ratios; chance 25%) 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 2029. 14 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Flash35.7#175
2InternVL3-8B32#1782
3Qwen 3.5 35B A3B31.4#492
4Meissa-4B30.8
5LLaVA-OneVision-7B30.4#2981
6Qwen 3.5 9B29.3#828
7Qwen 3 VL 4B29.1#1151
8HuatuoGPT-Vision-7B28.2#2162
9Qwen 3 VL 8B27.7#917
10M3D-LaMed-Phi-3-4B25
11MedGemma 1.5 4B24.6#2716
12LLaVA-Med23.4
13M3D-LaMed-Llama-2-7B23.3
14RadFM21.7

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=deeptumorvqa-measurement · How It Works · Data refreshed daily, snapshot 2026-11-21.