Kaggle RSNA Knee AUC10 - Vision (Large): leaderboard
Vision-only knee MRI label-extraction benchmark on Kaggle (kirderf/rsna-knee-llm-label-extraction-benchmark-auc10) measuring macro ROC-AUC (%) over 12 radiology findings across 10 radiologist-labeled consensus gold studies using large image mosaics.
Metric: Macro ROC-AUC (%). Source: www.kaggle.com. Saturation forecast: Around March 2027. 26 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6.1 Sol | 86.42 | #15 |
| 2 | GPT-6 Luna | 78.39 | #105 |
| 3 | GPT-5.6 Luna | 77.09 | #131 |
| 4 | GPT-5.5 | 75.74 | #54 |
| 5 | GPT-5.6 Sol | 67.66 | #37 |
| 6 | Claude Sonnet 5.5 | 66.41 | #24 |
| 7 | GPT-5.4 Mini | 66.31 | #406 |
| 8 | Gemini 3.1 Pro (Preview) | 65.69 | #99 |
| 9 | Claude Opus 5.5 | 64.13 | #9 |
| 10 | GPT-5.6 Terra | 62.92 | #71 |
| 11 | Gemini 3.8 Flash | 62.74 | #43 |
| 12 | Gemini 2.5 Pro | 61.79 | #276 |
| 13 | Gemini 4 Argon | 61.07 | #19 |
| 14 | Gemma 4 31B | 60.88 | #382 |
| 15 | Claude Haiku 4.5 | 59.81 | #583 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=kaggle-rsna-knee-auc10-vision-large · How It Works · Data refreshed daily, snapshot 2026-11-21.