Kaggle RSNA Knee AUC10 - Vision (Medium): 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 medium image mosaics.

Metric: Macro ROC-AUC (%). Source: www.kaggle.com. Saturation forecast: Around August 2027. 28 models tracked. Updated 21 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-6.1 Sol83.91#15
2GPT-5.6 Sol82.33#37
3GPT-6 Astra82.1#10
4GPT-5.579.39#54
5GPT-5.6 Terra71.29#71
6Claude Opus 5.570.26#9
7Gemini 4 Argon65.16#19
8GPT-6 Luna65.02#105
9Gemini 3.8 Flash62.77#43
10GPT-5.462.17#135
11GPT-5.6 Luna61.81#131
12Gemini 3.1 Flash Lite (Preview)60.13#417
13GPT-OSS-20B57.63#1183
14Gemma 4 31B56.83#382
15Claude Sonnet 5.556.83#24

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-medium · How It Works · Data refreshed daily, snapshot 2026-11-21.