OncoTriad-QA - Genomics Findings: leaderboard
Multiple-choice accuracy on the case-specific genomics-findings questions of OncoTriad-QA (2026), a patient-level pan-cancer question-answering benchmark over TCGA cases with radiology, pathology, genomic and clinical inputs, with all modalities available and averaged over three runs on a fixed sample of held-out test items. Higher is better.
Metric: Accuracy (%) on the case-specific genomics-findings questions of OncoTriad-QA's held-out TCGA cases in the all-available modality setting (representative pathology ROI images, radiology slices, genomic summaries and clinical metadata): multiple choice, mean of three runs over a frozen stratified 60% sample of the held-out test items; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 30.5 | #123 |
| 2 | MedGemma-4B-IT | 23.6 | #2716 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=oncotriad-qa-genomics-findings · How It Works · Data refreshed daily, snapshot 2026-11-13.