Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Open-ended Evaluation on RadBench open-ended reduced split n=69

2RadGraph F1

HR1.5

-0.080.4611.54Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.07
213.373.985.84.94737.1
2026.07
0.827.45879.31.720.131
0.71.87192.18.560.835.1
2026.07
0.611.278.388.55.349.733.3
0.64631.965.40.26.524.9
2026.07
0.328.759.478.8017.328.4
014.959.487.23.650.612.8
012.25888.6048.916.5