Models

Qwen 2.5

32b

Warm

qwen25-32b

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

1,475

2,453,014

D
Warm

qwen25-32b

Qwen/Qwen2.5-Coder-32B-Instruct

1,959

309,882

Q
Warm

qwen25-32b

Qwen/Qwen2.5-32B-Instruct

309

291,984

Q
Warm

qwen25-32b

baichuan-inc/Baichuan-M2-32B

116

179,923

B
Warm

qwen25-32b

Qwen/Qwen2.5-32B

169

145,294

Q
Warm

qwen25-32b

huihui-ai/Qwen2.5-32B-Instruct-abliterated

39

88,343

H
Warm

qwen25-32b

Qwen/QwQ-32B-Preview

1,741

62,629

Q
Warm

qwen25-32b

Qwen/QwQ-32B

2,872

56,896

Q
Warm

qwen25-32b

Qwen/Qwen2.5-Coder-32B

136

11,162

Q
Warm

qwen25-32b

unsloth/Qwen2.5-32B-Instruct

3

3,476

U
Warm

qwen25-32b

BytedTsinghua-SIA/DAPO-Qwen-32B

12

3,254

B
Warm

qwen25-32b

abeja/ABEJA-Qwen2.5-32b-Japanese-v1.0

5

2,809

A
Warm

qwen25-32b

unsloth/Qwen2.5-Coder-32B-Instruct

7

2,137

U
Warm

qwen25-32b

LLM360/K2-Think

362

1,873

L
Warm

qwen25-32b

huihui-ai/QwQ-32B-abliterated

99

1,672

H
Warm

qwen25-32b

simplescaling/s1.1-32B

96

1,636

S
Warm

qwen25-32b

nvidia/OpenReasoning-Nemotron-32B

119

1,452

N
Warm

qwen25-32b

rombodawg/Rombos-LLM-V2.5-Qwen-32b

63

1,369

R
Warm

qwen25-32b

huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated

235

902

H
Warm

qwen25-32b

SWE-bench/SWE-agent-LM-32B

68

614

S