Llama-3.1-Nemotron-70B-Instruct
NVIDIA- Arena score
- 1283
- Among open models
- #93of 148
- Among all on Arena
- #271
- Votes
- 7,140
Measured on Llama 3.1 Nemotron 70B Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1315#88#2573.7K
- Legal & government1303#87#252489
- Medicine & health1301#84#246392
- Science1293#90#2671.3K
- Applied math1287#84#253874
- Software & IT1283#97#2792.1K
- Hard prompts, English1283#94#2711.1K
- Multi-turn1275#91#2731.2K
- Coding1272#96#2831.3K
- Math1271#87#2651K
- Creative writing1268#83#2561K
- Hard prompts1266#96#2772K
- Chinese1263#88#267723
- Business & finance1262#89#265904
- Writing & literature1253#94#2891.8K
- Instructions1252#93#2783K
- Media & sports1249#89#268961
- Non-English1245#97#2873.4K
- Expert1242#94#268453
- Long prompts1238#102#2991K
- Russian1227#102#3001.1K
- Excluding ties1211#93#2714.7K
About as strong, smaller
Compare
granite-4.2-3bIBM Granite12923.7B
gemma-3-4b-itGoogle12914.3B

gemma-3n-E4B-itGoogle13067.8B

Molmo2-8BAi212878.7B
Built on it
Most downloaded
BenchClub runs
Not runnable yet
Runs open once a Llama-3.1-Nemotron-70B-Instruct build is registered.
More from NVIDIA
See moreOther 40–80B models
See more
Qwen3-Coder-NextQwen347.7K79.7B

Llama-3.3-70B-InstructMeta Llama344.4K70.6B

Mixtral-8x7B-Instruct-v0.1Mistral AI325.3K46.7B

falcon-40bTII11.6K41.8B