Qwen1.5-7B-Chat

Qwen
Arena score
1084
Among open models
#136of 148
Among all on Arena
#380
Votes
4,737

Measured on Qwen1.5-7B-Chat, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • Chinese1141
  • Applied math1108
  • Coding1107
  • English1105
  • Legal & government1103
  • Software & IT1090
  • Long prompts1090
  • Math1080
  • Science1076
  • Hard prompts, English1075
  • Hard prompts1065
  • Writing & literature1064
  • Business & finance1064
  • Multi-turn1061
  • Non-English1058
  • Instructions1058
  • Medicine & health1056
  • Expert1055
  • Creative writing1034
  • Media & sports1030
  • Russian1006
  • Excluding ties907

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
14
Fine-tunes
51
Adapters
19
Merges
3

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Qwen1.5-7B-Chat build is registered.

More from Qwen

See more

Other 3–9B models

See more