GPQA
Benchmarks
TaskDatasetSOTA resultTrendResults
GPQA
84.2Accuracy
258
GPQA
95.1Accuracy
243
GPQA
96.9Accuracy
224
GPQA Diamond
91.9Accuracy
185
GPQA
82.34Accuracy
138
GPQA Diamond
84.4Accuracy
131
GPQA Main
67.97Accuracy
115
Super GPQA
71.1Accuracy
99
GPQA Diamond
68.4Accuracy
97
GPQA Diamond
74.24Accuracy
94
GPQA
71.43Accuracy
92
GPQA
90.1Pass@1
92
GPQA Diamond (test)
99.37Accuracy
88
GPQA
87.6pass@1 Accuracy
85
GPQA Diamond
91.9Accuracy
84
GPQA-D
66.2Accuracy (%)
77
GPQA
70.2Accuracy
75
GPQA Diamond
80.13Accuracy
73
GPQA
59.22Accuracy (GPQA)
72
GPQA
61.95Accuracy (GPQA)
72
GPQA Diamond
83Accuracy
72
GPQA
63.51Accuracy
69
GPQA
55.8Accuracy
69
GPQA Diamond
73.2Score
68
GPQA Diamond
78.66Pass@1 Accuracy
67