HLE
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HLE
85Avg Score
75
HLE Math-100
35.84Pass@1
68
HLE
64.7Score
65
HLE
40.8Accuracy (HLE Reasoning)
63
HLE
0.723Accuracy
62
HLE
60Performance
41
HLE
48.8Accuracy
33
HLE Maths
38.2Accuracy
31
HLE (test)
49Pass@1
25
HLE Gold 149
80.5Accuracy (Bio)
25
HLE
67.1Accuracy
25
HLE
54Accuracy
25
HLE
13.37HLE Score
24
HLE
38.4Accuracy
21
HLE
8.12Pass@1
20
HLE
100Head-to-head Win %
20
HLE
612pass@1
17
HLE
26.6Average Score
17
HLE
4.36Accuracy
16
HLE
50.2Accuracy
16
HLE math
23.3Accuracy
16
HLE
51Accuracy
16
hle
11.4Accuracy
16
HLE Text
62Score
15
HLE
37.6Accuracy
15