Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Response Length (Tokens) on GSM8K
Loading...
501
Response Length (Tokens)
DeepSeek-R1-Distill
231.64
301.57
371.5
441.43
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
501
DeepSeek-R1-Distill
Model Scale=7B, Base M...
2026.06
465
AdaCoT
Model Scale=1.5B, Base...
2026.06
443
AdaCoT
Model Scale=7B, Base M...
2026.06
422
AdaptThink
Model Scale=1.5B, Base...
2026.06
337
SuCo
Model Scale=1.5B, Base...
2026.06
304
S-GRPO
Model Scale=1.5B, Base...
2026.06
297
LHRMs
Model Scale=7B, Base M...
2026.06
274
S-GRPO
Model Scale=7B, Base M...
2026.06
267
AdaptThink
Model Scale=7B, Base M...
2026.06
247
SuCo
Model Scale=7B, Base M...
2026.06
243
LHRMs
Model Scale=1.5B, Base...
2026.06
242
Feedback
Search any
task
Search any
task