Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Agentic Coding on LiveCodeBench
Loading...
56
Pass@1
ALIVE-Self
54.232
54.691
55.15
55.609
Feb 5, 2026
Pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1
ALIVE-Self
Backbone=Qwen3-30B-Ins...
2026.02
56
ALIVE-Oracle
Backbone=Qwen3-30B-Ins...
2026.02
55.8
GRPO (Scalar Reward)
Backbone=Qwen3-30B-Ins...
2026.02
55.4
SFT
Backbone=Qwen3-30B-Ins...
2026.02
55.1
FCP (Verbal Only)
Backbone=Qwen3-30B-Ins...
2026.02
54.9
Base Model
Backbone=Qwen3-30B-Ins...
2026.02
54.3
Feedback
Search any
task
Search any
task