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

Code Generation on MBPP (average acceptance length (τ), Speedup)

8.99Average Acceptance Length (τ)

BASTION

1.84523.70015.5557.4099May 19, 2026May 26, 2026Jun 2, 2026Jun 9, 2026Jun 16, 2026Jun 23, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.05
8.997.41
2026.05
8.786.75
2026.05
8.777.07
2026.05
8.657.1
2026.06
7.436.73
2026.05
7.115.59
2026.05
7.045.53
2026.06
6.956.31
2026.06
6.836.11
2026.06
6.76.09
2026.06
6.424.38
2026.06
6.395.78
2026.05
6.364.96
2026.06
6.334.59
2026.05
6.315.09
2026.06
6.285.7
2026.06
6.264.53
2026.06
6.244.26
2026.06
6.174.54
2026.05
6.164.46
2026.05
6.124.77
2026.06
6.125.49
2026.05
6.044.91
2026.05
6.024.73
2026.06
5.994.33
2026.05
5.984.71
2026.05
5.934.16
2026.05
5.884.73
2026.06
5.885.34
2026.06
5.755.22
2026.05
5.674.44
2026.06
5.544.02
2026.06
5.515
2026.06
5.494.99
2026.05
5.444.13
2026.06
5.423.92
2026.06
5.413.98
2026.05
5.234.14
2026.06
5.114.65
2026.06
5.034.03
2026.06
53.68
2026.06
4.983.96
2026.06
4.963.97
2026.06
4.863.51
2026.06
4.713.22
2026.06
4.513.6
2026.06
4.433.52
2026.06
4.423.21
2026.06
4.413.52
2026.06
4.393.51
2026.06
4.363.2
2026.06
4.013.02
2026.06
3.973.17
2026.06
3.972.71
2026.06
3.852.9
2026.06
3.812.22
2026.06
3.712.69
2026.06
3.72.13
2026.06
3.62.09
2026.06
3.52.02
2026.05
3.442.3
2026.05
3.382.19
2026.05
3.312.24
2026.05
3.312.22
2026.06
3.311.95
2026.05
3.242.11
2026.06
3.221.89
2026.06
3.212.32
2026.06
3.172.16
2026.06
3.12.25
2026.06
3.051.71
2026.06
3.032.23
2026.05
3.012.47
2026.05
3.012.46
2026.05
2.992.02
2026.05
2.982.39
2026.05
2.982.39
2026.05
2.982.45
2026.06
2.961.61
2026.05
2.951.97
2026.05
2.951.97
2026.06
2.951.78
2026.06
2.922.24
2026.06
2.891.69
2026.05
2.861.93
2026.06
2.842.18
2026.06
2.821.69
2026.06
2.741.64
2026.05
2.482.77
2026.05
2.442.04
2026.05
2.412.7
2026.05
2.242.73
2026.05
2.232.52
2026.06
2.161.7
2026.06
2.121.66