Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Graph Optimization on FORGE-BENCH

100Success Rate (SR)

gpt-o3

-4235077May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
10051.4
2026.05
10055.8
2026.05
10050.4
2026.05
10053
2026.05
10051.7
2026.05
10051.8
2026.05
9951.2
2026.05
9952.6
2026.05
9953.8
2026.05
9877.1
2026.05
9851
2026.05
9786.4
2026.05
9648.6
2026.05
9649.7
2026.05
93.146.6
2026.05
91.576.9
2026.05
91.351.3
2026.05
9039.5
2026.05
89.727.8
2026.05
8932.2
2026.05
8944.3
2026.05
88.879.9
2026.05
8678.2
2026.05
8643.3
2026.05
82.370.7
2026.05
76.864.1
2026.05
70.757.6
2026.05
6734
2026.05
66.762.9
2026.05
65.450.2
2026.05
64.729.3
2026.05
62.136.2
2026.05
57.545.4
2026.05
57.350.6
2026.05
56.843
2026.05
53.939.9
2026.05
4737.9
2026.05
44.739.3
2026.05
43.426.5
2026.05
41.221.8
2026.05
36.217.8
2026.05
35.716.8
2026.05
35.315.2
2026.05
3529.3
2026.05
34.829.2
2026.05
34.715.2
2026.05
3216.2
2026.05
3011.5
2026.05
29.614.6
2026.05
23.318.1
2026.05
238
2026.05
22.716.8
2026.05
1813.4
2026.05
15.15.8
2026.05
153.6
2026.05
13.84.9
2026.05
113.1
2026.05
7.72.9
2026.05
6.31.9
2026.05
62.2
2026.05
4.72.5
2026.05
21
2026.05
00