Student
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Student_15 1.0 (test)
27.37ROUGE-L
72
Student 100 1.0 (test)
0.303ROUGE-L
72
student
97.5RA
16
Student Port
92.76AU-ARC
15
Student_15 v1.0 (test)
3.65Con2
15
student
85.7Performance
14
student
85.7Performance
13
student
86Accuracy / R2 Score
13
Student
98.4AUC
8
Student three random (train-test)
94.3Accuracy
8
Student (held-out test)
100Success Rate
7
Student
4.56PPL
7
student
19.62Accuracy
7
Student
100Success Rate
6
Student (test)
97Coverage Rate
5
Student (test)
4Max Rule Width
5
Student w/ Reasoning
16Student Leakage
3
Student (test)
24GT Found Count
3
Student
2.43Runtime (Time)
2
Student
2.43Runtime
2
Student_1361 OS_124
12.4Accuracy
2
Student 1361 Java 200 (subset)
17.5Accuracy
2
Student_1361 Discrete_106
26.5Accuracy
2
Student random splits (test)
0.9Relative Error Rate Reduction
2
Student-48
56,920,256PRAXIS Count
1