Llama-3.3-70B-Instruct
Meta Llama- Arena score
- 1274
- Among open models
- #96of 148
- Among all on Arena
- #281
- Votes
- 54,476
Measured on Llama 3.3 70B Instruct, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- English1303#92#26729.2K
- Legal & government1284#93#2683.2K
- Science1284#94#2769.4K
- French1281#71#227574
- Multi-turn1279#89#2689.1K
- Hard prompts, English1277#97#2809.5K
- Medicine & health1275#92#2652.7K
- Software & IT1273#98#28714.8K
- Spanish1269#77#235634
- Coding1268#98#2898.7K
- Applied math1267#92#2755.2K
- Math1267#89#2735.8K
- Polish1259#71#2221.5K
- Hard prompts1257#98#28317K
- Long prompts1255#96#2888.3K
- Writing & literature1255#92#28613.8K
- Russian1252#93#2815.7K
- German1251#76#2371.2K
- Creative writing1250#91#2718K
- Business & finance1243#98#2836.6K
- Instructions1242#97#28918.8K
- Media & sports1241#92#2769.7K
- Non-English1236#98#29225.2K
- Expert1225#97#2782.9K
- Chinese1217#99#3013.7K
- Excluding ties1199#96#28236.7K
- Japanese1151#69#2381.2K
- Korean1143#77#248856
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
Top 10 among open models in#10Merges
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/Llama-3.3-70B-Instruct-GGUF45 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/Llama-3.3-70B-Instruct-4bit9 builds
- AWQ · vLLM, SGLangkosbu/Llama-3.3-70B-Instruct-AWQ12 builds
- GPTQ · vLLM, SGLangSatwik11/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit3 builds
Most downloaded
- Llama-3.3-70B-Instruct-GGUFbartowski · Quantization216.6K downloads
- Llama-3.3-70B-Instruct-AWQkosbu · Quantization85.5K downloads
- Llama-3.3-70B-Instruct-FP8-dynamicRedHatAI · Quantization53K downloads
- Llama-3.3-70B-Instruct-GGUFunsloth · Quantization47K downloads
- Llama-3.3-70B-Instructunsloth · Fine-tune38.2K downloads
BenchClub runs
Not runnable yet
Runs open once a Llama-3.3-70B-Instruct build is registered.
More from Meta Llama
See more
Llama-3.1-8B-Instruct4.2M8.0B

Llama-3.2-1B-Instruct1.3M1.2B

Llama-3.2-3B-Instruct831.4K3.2B

Llama-3.2-1B644.1K1.2B
Other 40–80B models
See more
Qwen3-Coder-NextQwen347.7K79.7B

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

falcon-40bTII11.6K41.8B
Jamba-v0.1AI21 Labs4.5K51.6B