Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Competitive Programming on LiveCodeBench (avg@8)
Loading...
82.6
Avg@8
SD-ZERO
30.392
43.946
57.5
71.054
Apr 13, 2026
Avg@8
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@8
SD-ZERO
Base Model=Qwen3-4B-In...
2026.04
82.6
SRT
Base Model=Qwen3-4B-In...
2026.04
74.4
RFT
Base Model=Qwen3-4B-In...
2026.04
68
GRPO
Base Model=Qwen3-4B-In...
2026.04
62.6
Qwen3-4B-Instruct
Base Model=Qwen3-4B-In...
2026.04
61.8
SRT
Base Model=Olmo-3-7B-I...
2026.04
59.6
SDFT
Base Model=Qwen3-4B-In...
2026.04
59.2
SD-ZERO
Base Model=Olmo-3-7B-I...
2026.04
57.8
SFT
Base Model=Qwen3-4B-In...
2026.04
57.2
RFT
Base Model=Olmo-3-7B-I...
2026.04
49.4
GRPO
Base Model=Olmo-3-7B-I...
2026.04
43.6
SDFT
Base Model=Olmo-3-7B-I...
2026.04
42.3
SFT
Base Model=Olmo-3-7B-I...
2026.04
41
Olmo-3-7B-Instruct
Base Model=Olmo-3-7B-I...
2026.04
32.4
Feedback
Search any
task
Search any
task