GPQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GPQA Diamond
65Pass@1
17
GPQA
81.4Score
17
GPQA Diamond
44.8Avg@4 Accuracy
17
GPQA General
32.4Pass@1
17
GPQA-D
61.1Score
16
GPQA Diamond
69.19GPQA Score
16
GPQA Diamond
67.17Pass@4 Accuracy
16
GPQA
72.7multi@5 Accuracy
16
GPQA
41.7Avg@32 Accuracy
16
GPQA Main
98.39LLM Trust Score
16
GPQA
75.39Throughput
16
GPQA Diamond
69.2Accuracy
16
GPQA Diamond (out-of-distribution)
69.2Accuracy
16
GPQA
32.84Score
16
GPQA (test)
70.8Pass@1
16
GPQA-D
77.46Avg@k
16
GPQA
40.91Accuracy
16
GPQA Diamond
70.2Accuracy
16
GPQA Diamond
86.7Seed Score
16
GPQA
14.7Inference Time: Research And Data
16
GPQA Diamond
75.4Accuracy (avg@8)
16
GPQA Diamond (test)
37.4Accuracy
16
GPQA
91.96Pass@16
16
GPQA
39.4Avg@4
16
GPQA Diamond (test)
49Pass@1
16