DDx-TRACE - Essential Evidence Recall: leaderboard
DDx-TRACE (2026) scores diagnostic trajectories on physician-adjudicated neuroradiology cases: models request imaging in free form, update a probabilistic differential diagnosis after each turn and stop with a localized diagnosis, judged against case rubrics. This board scores the share of physician-labelled essential imaging exams the model requested, on a 0 to 1 scale; higher is better.
Metric: Essential-evidence recall (0-1): share of the physician-labelled essential imaging exams the model requested on DDx-TRACE (211 physician-adjudicated multimodal neuroradiology cases), the model starts from limited history, requests imaging in free form (at most 6 requests), updates a four-item probabilistic differential after each turn and stops with a localized diagnosis, provider default decoding; endpoints judged against case rubrics by Gemini 3 Flash at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 0.767 | #180 |
| 2 | Gemini 3.1 Pro (Preview) | 0.722 | #102 |
| 3 | GPT-5.4 | 0.716 | #138 |
| 4 | Claude Sonnet 4.6 | 0.714 | #179 |
| 5 | Qwen 3.5 27B | 0.598 | #380 |
| 6 | Lingshu-32B | 0.598 | #1125 |
| 7 | MedGemma-27B-IT | 0.579 | #1359 |
| 8 | Qwen 3.5 4B | 0.541 | #1270 |
| 9 | Qwen 3.5 9B | 0.526 | #838 |
| 10 | Gemma 3 27B | 0.508 | #1672 |
| 11 | Qwen 3.5 35B A3B | 0.426 | #494 |
| 12 | GPT-5.4 Mini | 0.425 | #409 |
| 13 | MedGemma 1.5 4B | 0.26 | #2742 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=ddx-trace-essential-evidence-recall · How It Works · Data refreshed daily, snapshot 2026-11-22.