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

Question Answering on GPQA (Throughput, Speedup, Acceptance Length)

75.39Throughput

STAND

15.870831.322946.77562.2271Jun 5, 2025
Updated 12d ago

Evaluation Results

MethodLinks
2025.06
75.392.413.05
2025.06
71.512.282.81
2025.06
712.272.71
2025.06
54.051.721.82
2025.06
48.451.551.69
2025.06
42.841.371.64
2025.06
38.912.142.73
2025.06
38.712.133
2025.06
37.532.072.72
2025.06
31.691.011.99
2025.06
31.34--
2025.06
26.41.451.79
2025.06
25.381.41.65
2025.06
24.971.381.64
2025.06
24.861.372.44
2025.06
18.16--