MedFlowBench (Radiology) - Task: leaderboard
Metric: Task score (0-1, shown times 100) before any evidence check (accuracy, or the share of the five labels right for lung PET/CT), averaged without weights over the three radiology modules (LUMIERE longitudinal brain MRI (139 questions: RANO response category from baseline and follow-up studies); UCSF-PDGM multi-sequence brain MRI (495 cases: tumor diagnosis); NSCLC lung PET/CT (162 cases: tumor location, pathological T and N stage, histology and grade)); the model drives 3D Slicer through the MedOpenClaw runtime with viewer-native actions only (series selection, scrolling, windowing, prealigned fusion), inspecting the complete study within a 20-round budget and returning an answer with structured evidence (Track A); higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 53 | #54 |
| 2 | GPT-5.5 | 53 | #26 |
| 3 | Gemini 3 Flash (Preview) | 47 | #78 |
| 4 | Qwen 3.5 35B A3B | 40 | #250 |
| 5 | Qwen 3.5 27B | 37 | #183 |
| 6 | Claude Opus 4.7 | 36 | #45 |
| 7 | Gemma 3 27B (IT) | 33 | #509 |
| 8 | Claude Sonnet 4.6 | 32 | #85 |
| 9 | GPT-5.4 Mini | 31 | #202 |
| 10 | MedGemma 1.5 4B | 26 | #775 |
| 11 | Qwen 3.5 4B | 25 | #470 |
| 12 | Qwen 3.5 9B | 23 | #363 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=medflowbench-radiology-task · How It Works · Data refreshed daily, snapshot 2026-10-11.