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

GPQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringGPQA
Accuracy84.2
258
Science ReasoningGPQA
Accuracy95.1
243
Graduate-level Question AnsweringGPQA
Accuracy96.9
184
ReasoningGPQA Diamond
Accuracy91.9
135
Question AnsweringGPQA Diamond
Accuracy68.4
97
General ReasoningSuper GPQA
Accuracy71.1
89
Science Question AnsweringGPQA
pass@1 Accuracy87.6
85
Scientific ReasoningGPQA
Accuracy70.2
75
Scientific ReasoningGPQA Diamond
Score73.2
68
Scientific ReasoningGPQA Main
Accuracy43.08
67
Scientific Question AnsweringGPQA Diamond
Accuracy84.4
64
Closed-ended reasoningGPQA Diamond (test)
Accuracy65.9
63
Science Question AnsweringGPQA main (test)
Exact Match Accuracy40.85
60
ReasoningGPQA
Accuracy59.4
57
Scientific ReasoningGPQA
Accuracy83.8
55
Question AnsweringGPQA (test)
Accuracy45.5
55
Scientific ReasoningGPQA Diamond
Pass@1 Accuracy66.8
54
KnowledgeGPQA
Accuracy90.4
51
Science ReasoningGPQA
Pass@170.2
50
Question AnsweringGPQA Diamond
Pass@175.7
49
Scientific ReasoningGPQA Diamond
Accuracy87.5
48
General ReasoningGPQA Diamond
Pass@1 Accuracy86.4
47
Science Question AnsweringGPQA
Accuracy91.5
46
Science Question AnsweringGPQA
Accuracy34.8
46
Science Question AnsweringGPQA
Accuracy54.5
42
Showing 25 of 322 rows
...