Humanity's Last Exam
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Humanity's Last Exam
84.61Accuracy
60
Humanity's Last Exam Math (test)
29.76Accuracy
28
Humanity's Last Exam
14.7NS Score
22
Humanity's Last Exam
41.6Avg@3
19
Humanity's Last Exam
50Score
17
Humanity's Last Exam
51.7Pass@1
16
Humanity's Last Exam 2,158 text-only
54.2Avg@3 Score
15
Humanity's Last Exam
40.9Accuracy
14
Humanity's Last Exam (HLE)
18.4Pass@1 Score
13
Humanity's Last Exam
38.3Pass@1
11
Humanity's Last Exam (HLE) curated 649-question subset (test)
54.3Accuracy
7
Humanity’s Last Exam (HLE) Open-web via SERPER (test)
14.8Pass@4
6
Humanity's Last Exam (HLE)
8.81Bio Accuracy (average@8)
6
Humanity's Last Exam (HLE) MCQ
19.9Accuracy
6
Humanity's Last Exam AA-LCR
54.3Accuracy
6
HUMANITY’S LAST EXAM text-only
11.1Score
4