Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

OlympiadBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningOlympiadBench Math
Accuracy99.86
84
Mathematical ReasoningOlympiadBench Math (test)
Accuracy35.9
59
Math ReasoningOlympiadBench
Accuracy90.7
54
Mathematical ReasoningOlympiadBench
Accuracy65.81
48
Mathematical ReasoningOlympiadBench
Pass@162.1
39
Mathematical ReasoningOlympiadBench
Pass Rate60.67
36
Mathematical ReasoningOlympiadBench
Accuracy0.7659
34
Mathematical ReasoningOlympiadBench
Accuracy65.3
30
Mathematical ReasoningOlympiadBench
EM14.7
30
Mathematical ReasoningOlympiadBench
Accuracy0.44
24
Mathematical ReasoningOlympiadBench
Avg Success Rate @844.25
23
Math ReasoningOlympiadBench
Accuracy70.3
22
Math ReasoningOlympiadBench
Pass@1 Accuracy48.2
19
Mathematical ReasoningOlympiadBench Math
Pass@127
18
Mathematical ReasoningOlympiadBench
Accuracy (Pass@1)73.3
17
Mathematical ReasoningOlympiadBench
Pass@1673.6
16
Mathematical ReasoningOlympiadBench (OLY.)
Pass@138.2
16
Mathematical ReasoningOlympiadbench
Average@1660.6
15
Scientific ReasoningOlympiadBench Physics
Accuracy87.3
14
Process-level verificationOlympiadBench ProcessBench (test)
Error8.2
13
Mathematical ReasoningOlympiadBench
Pass@145.2
12
Mathematical ReasoningOlympiadBench
Avg@1650.7
12
Mathematical ReasoningOlympiadBench
Avg@336
12
Mathematical ReasoningOlympiadBench OE_TO_maths_en_COMP
Accuracy74.04
12
Mathematical ReasoningOlympiadBench
Pass@164
12
Showing 25 of 43 rows