Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code generation on LiveBench (Pass@K, GSS@K)
Loading...
20.39
Pass@10
Qwen2.5-VL-72B-Ins
8.2532
11.4041
14.555
17.7059
Sep 29, 2025
Pass@10
Pass@1
Pass@32
GSS@10
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@10
Pass@1
Pass@32
GSS@10
Qwen2.5-VL-72B-Ins
2025.09
20.39
-
22.37
-
GRPO
TN=16, AN=1, S/S=186.91
2025.09
11.92
6.3
14.12
25
GRPO-MA
TN=4, AN=4, S/S=93.45
2025.09
11.69
6.73
14.7
10
GRPO
TN=4, AN=1, S/S=76.21
2025.09
11.56
6.59
13.7
6
GRPO
TN=8, AN=1, S/S=104.83
2025.09
11.44
6.53
13.39
24
Qwen2.5-VL-7B-Ins
2025.09
10.72
-
11.31
-
Qwen2.5-VL-3B-Ins
2025.09
9.8
-
11.67
-
SFT
2025.09
8.72
-
10.59
-
Feedback
Search any
task
Search any
task