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

Symbolic Reasoning on OlyBench

36.5Accuracy

QuaSAR

5.313.421.529.6Feb 18, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.02
36.5
2025.02
32.2
2025.02
27.8
2025.02
16.6
2025.02
14.7
2025.02
14.6
2025.02
13.2
2025.02
13
2025.02
12.4
2025.02
11.8
2025.02
10.9
2025.02
10.9
2025.02
10.7
2025.02
10.6
2025.02
10.5
2025.02
9.8
2025.02
9.8
2025.02
9.1
2025.02
8.2
2025.02
8.2
2025.02
7.8
2025.02
7.4
2025.02
7.1
2025.02
6.9
2025.02
6.5