Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on LiveCodeBench (Accuracy and Absolute Accuracy Change)
Loading...
83.33
Accuracy
SKILLGEN
26.8268
41.4959
56.165
70.8341
Feb 26, 2026
Mar 10, 2026
Mar 22, 2026
Apr 3, 2026
Apr 15, 2026
Apr 27, 2026
May 9, 2026
Accuracy
Absolute Accuracy Change
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Absolute Accuracy Change
SKILLGEN
Model Name=Gemma-4-26B...
2026.05
83.33
0
SKILLGEN
Model Name=GPT-5.4-Min...
2026.05
65.33
6
Dynamic-MAS + PRM
Backbone=Qwen3-14B
2026.02
33
-
Dynamic-MAS + Self-Refine
Backbone=Qwen3-14B
2026.02
32.5
-
Dynamic-MAS + ADv2
Backbone=Qwen3-14B
2026.02
32
-
Single Agent
Backbone=Qwen3-14B
2026.02
29.5
-
Dynamic-MAS + Multi-TAG
Backbone=Qwen3-14B
2026.02
29.5
-
Dynamic-MAS
Backbone=Qwen3-14B
2026.02
29
-
Feedback
Search any
task
Search any
task