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

General Evaluation on Average Across all benchmarks

6.9Speedup

BASTION

1.97043.25024.535.8098May 28, 2026May 29, 2026May 30, 2026May 31, 2026Jun 1, 2026
Updated 20h ago

Evaluation Results

MethodLinks
2026.05
6.98.24
2026.05
6.888.38
2026.05
6.468.36
2026.05
6.428.25
2026.06
5.527.47
2026.06
5.467.33
2026.05
5.276.1
2026.05
5.176.09
2026.06
5.056.39
2026.06
4.996.47
2026.05
4.585.33
2026.06
4.536.21
2026.05
4.355.19
2026.06
4.355.6
2026.06
4.335.9
2026.06
4.165.3
2026.06
3.914.93
2026.06
3.714.66
2026.05
2.992.47
2026.05
2.752.33
2026.05
2.62.29
2026.06
2.563.39
2026.05
2.512.16
2026.06
2.493.62
2026.06
2.493.26
2026.06
2.353.47
2026.06
2.33.51
2026.06
2.163.3