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

HMMT25

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningHMMT25
Accuracy86.7
119
Mathematical ReasoningHMMT25
Accuracy (%)92.5
115
Mathematical ReasoningHMMT25
Avg@3217.9
34
Mathematical ReasoningHMMT25
Pass@1653.3
24
Mathematical ReasoningHMMT25
Avg@12 Accuracy48.1
21
Mathematical ReasoningHMMT25
Accuracy (HMMT25)16.3
21
Math ReasoningHMMT25
Accuracy (HMMT25)34.9
21
Mathematical ReasoningHMMT25
Mean Score (8 samples)13.33
18
Mathematical ReasoningHMMT25
Accuracy33.6
16
Math ReasoningHMMT25
Pass@866.7
14
MathHMMT25
Avg@1644.5
12
Mathematical ReasoningHMMT25
Average Score46.4
12
Long-chain Mathematical ReasoningHMMT25
Accuracy avg@3282.2
6
MathematicsHMMT25
Throughput (Req/s)16.83
6
Mathematical ReasoningHMMT25
Pass@853.33
5
Math reasoningHMMT25 Nov.
Mean@815.83
4
Showing 16 of 16 rows