Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on LiveCodeBench V6 (Response Length)
Loading...
11,073
Response Length (Tokens)
DeepSeek-R1-Distill
2,291.24
4,571.12
6,851
9,130.88
Jun 16, 2026
Response Length (Tokens)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Response Length (Tokens)
DeepSeek-R1-Distill
Model Scale=1.5B, Base...
2026.06
11,073
DeepSeek-R1-Distill
Model Scale=7B, Base M...
2026.06
10,407
AdaptThink
Model Scale=7B, Base M...
2026.06
8,911
AdaCoT
Model Scale=7B, Base M...
2026.06
8,153
AdaptThink
Model Scale=1.5B, Base...
2026.06
6,689
S-GRPO
Model Scale=7B, Base M...
2026.06
6,534
AdaCoT
Model Scale=1.5B, Base...
2026.06
6,455
S-GRPO
Model Scale=1.5B, Base...
2026.06
5,293
LHRMs
Model Scale=1.5B, Base...
2026.06
4,716
LHRMs
Model Scale=7B, Base M...
2026.06
4,294
SuCo
Model Scale=7B, Base M...
2026.06
2,809
SuCo
Model Scale=1.5B, Base...
2026.06
2,629
Feedback
Search any
task
Search any
task