Llama-2-7b-chat-hf

Meta Llama
Arena score
1053
Among open models
#142of 148
Among all on Arena
#396
Votes
14,148

Measured on Llama 2 7B Chat, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • English1096
  • Legal & government1065
  • Science1047
  • Math1042
  • Applied math1039
  • Writing & literature1037
  • Medicine & health1036
  • Expert1036
  • Creative writing1033
  • Hard prompts, English1032
  • Multi-turn1029
  • Software & IT1029
  • Business & finance1028
  • Media & sports1020
  • Hard prompts1009
  • Spanish1007
  • Instructions1006
  • Coding1002
  • Long prompts999
  • Russian995
  • German977
  • Chinese973
  • Non-English973
  • French970
  • Excluding ties861

Score by size

Plot against
Best for its size
ModelParamsScore
Llama-2-7b-chat-hf6.7B1053
Llama-2-7b-hf6.7B—
Llama-2-7b7.0B—
Llama-2-7b-chat7.0B—
Llama-2-13b-chat13.0B—
Llama-2-13b-chat-hf13.0B1084
Llama-2-70b-chat-hf69.0B1115
Llama-2-70b-chat70.0B—

About as strong, smaller

Compare

Discussion

Built on it

Quantizations
104
Fine-tunes
763
Adapters
1,208
Merges
5

Ways to run it

Most downloaded

BenchClub runs

Not runnable yet

Runs open once a Llama-2-7b-chat-hf build is registered.

More from Meta Llama

See more

Other 3–9B models

See more