MeniOmni - Severity Grading: leaderboard
Metric: Average quadratic weighted kappa (Avg-QWK, -1 to 1): mean of the medial and lateral compartment kappas, zero-shot Stoller grading (0 to 3) of the medial and lateral meniscus from sagittal, coronal and axial knee MRI sequences plus serialized age, sex and BMI, on the held-out test split (about a tenth of 746 cases from three centres, patient-level split), temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 0.59 |
| 2 | Claude 3.5 Sonnet | 0.56 |
| 3 | Gemini 1.5 Pro | 0.52 |
| 4 | Qwen 2 VL 72B | 0.49 |
Interactive version: theaggregate.ai/benchmark?slug=meniomni-severity-grading · How It Works · Data refreshed daily, snapshot 2026-10-07.