FrontierScience-Olympiad
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
FrontierScience-Olympiad
50.8Accuracy
63
FrontierScience-Olympiad
43.5Biology Accuracy
30
FrontierScience-Olympiad
5.59Token Efficiency Ratio (B_method/BMV)
27
FrontierScience Olympiad
80Accuracy
12
FrontierScience Olympiad
53Bonferroni Score
10
FrontierScience Olympiad N=20 (test)
—Primary metric
0