APPS
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
APPS
91.2Pass@1
111
APPS Interview
81AUROC
79
APPS Intro
0.813AUROC
79
APPS
80Accuracy
53
APPS
90.53Accuracy
42
APPS (test)
56.3Introductory Score
36
APPS Intermediate
81.95Pass Rate
32
APPS 1.0 (test)
0.988Safety Score
30
APPS
45Accuracy
29
APPS Introductory
92.1pass@1
25
APPS Competition
38pass@1
20
APPS
81.91Accuracy
18
APPS Overall
21.38PR
18
APPS
85.6Thoroughness
12
APPS
83.2Pass@4
12
APPS 1.0 (test)
25.61Pass@5 (Introductory)
11
APPS
5.65Tau
10
APPS Interview
2.64Pass@1
9
APPS interview-level (test)
0.572Mean Score
8
APPS-G
100Message Accuracy
8
APPS
0.96Correlation (rho)
7
APPS (val)
72.72Pass@1
6
APPS (test)
81.6pAUC
6
APPS Leetcode (test)
0.474RMSE
6
APPS+
1.94Pass@1 (Introductory)
5