Llama-3.1-8B-Instruct

Meta Llama
$ uv tool install "git+https://github.com/holaboss-ai/holaOS@feat/benchclub-cli#subdirectory=packages/benchclub"
$ benchclub login && benchclub run llama3.1:8b-instruct-q4_K_M

BenchClub cloud

No cloud result yet

Headline numbers come from BenchClub’s pinned cloud runner.

Arena score
1187
Among open models
#114of 148
Among all on Arena
#332
Votes
49,605

Measured on Llama 3.1 8B Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.

Score by category

CategoryScore
  • English1218
  • Legal & government1206
  • Hard prompts, English1196
  • Software & IT1195
  • Coding1195
  • Science1193
  • Medicine & health1182
  • Long prompts1181
  • Applied math1180
  • Math1179
  • French1177
  • Hard prompts1175
  • Multi-turn1172
  • Spanish1169
  • Business & finance1166
  • Writing & literature1162
  • Instructions1159
  • Russian1158
  • Creative writing1154
  • Chinese1151
  • Non-English1148
  • Media & sports1145
  • German1144
  • Expert1144
  • Japanese1061
  • Excluding ties1055
  • Korean1053

Score by size

Plot against
Best for its size
ModelParamsScore
Llama-3.1-8B8.0B—
Llama-3.1-8B-Instruct8.0B1187
Llama-3.1-70B-Instruct70.6B1261
Llama-3.1-405B-Instruct406B1284

About as strong, smaller

Compare

BenchClub runs

No runs yet

Be the first to benchmark Llama-3.1-8B-Instruct on your own hardware.

Discussion

Built on it

Top 10 among open models in#1Fine-tunes#2Quantizations#4Adapters#6Merges

Quantizations
967
Fine-tunes
3,320
Adapters
3,059
Merges
106

Ways to run it

Most downloaded

More from Meta Llama

See more

Other 3–9B models

See more