Qwen1.5-32B-Chat

Qwen
Arena score
1137
Among open models
#124of 148
Among all on Arena
#352
Votes
21,741

Measured on Qwen1.5-32B-Chat, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • Chinese1177
  • Applied math1163
  • English1160
  • Math1155
  • Coding1155
  • Hard prompts, English1147
  • Software & IT1147
  • Long prompts1146
  • Legal & government1140
  • Multi-turn1140
  • Science1132
  • Hard prompts1130
  • Expert1126
  • Writing & literature1118
  • Instructions1115
  • Medicine & health1111
  • Non-English1106
  • French1101
  • Business & finance1094
  • Spanish1089
  • Creative writing1083
  • Media & sports1080
  • Russian1073
  • German1058
  • Japanese1027
  • Korean1008
  • Excluding ties989

Score by size

Plot against
Best for its size
ModelParamsScore
Qwen1.5-4B-Chat4.0B997
Qwen1.5-7B-Chat7.7B1084
Qwen1.5-14B-Chat14.2B1128
Qwen1.5-32B-Chat32.5B1137
Qwen1.5-72B-Chat72.3B1166
Qwen1.5-110B-Chat111B1175

About as strong, smaller

Compare

Built on it

Quantizations
7
Fine-tunes
1
Adapters
3
Merges
0

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Qwen1.5-32B-Chat build is registered.

More from Qwen

See more

Other 20–40B models

See more