Meta-Llama-3-70B-Instruct
Meta Llama- Arena score
- 1221
- Among open models
- #108of 148
- Among all on Arena
- #315
- Votes
- 156,876
Measured on Llama 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
- English1277#101#29390.6K
- Spanish1241#84#2532.7K
- French1232#80#2512.5K
- Hard prompts, English1230#104#30429.6K
- Legal & government1228#104#3078.3K
- Science1226#106#31425.9K
- Multi-turn1223#103#30521.4K
- Math1218#101#30020.9K
- Medicine & health1214#102#2958.3K
- Applied math1214#104#30418.7K
- Creative writing1210#101#30522.8K
- Writing & literature1206#107#31937.7K
- Coding1206#108#31828.1K
- Software & IT1204#110#32145.1K
- Polish1196#76#236406
- Media & sports1195#104#30823.2K
- Hard prompts1195#109#31946K
- Instructions1194#109#31856.6K
- Long prompts1174#114#33217.5K
- Business & finance1172#111#32516.6K
- German1169#87#2735K
- Russian1159#113#33215K
- Expert1149#109#3148K
- Non-English1142#116#33866.3K
- Excluding ties1115#107#314103.8K
- Chinese1114#120#34215.9K
- Korean1017#87#2735.4K
- Japanese1017#85#2703.3K
| Model | Params | Score |
|---|---|---|
| 8.0B | — | |
| 8.0B | 1166 | |
| 70.6B | 1221 |
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
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioQuantFactory/Meta-Llama-3-70B-Instruct-GGUF-v216 builds
- AWQ · vLLM, SGLangpalisaderesearch/Badllama-3-70B1 build
- GPTQ · vLLM, SGLangMaziyarPanahi/Meta-Llama-3-70B-Instruct-GPTQ2 builds
Most downloaded
- calme-2.2-llama3-70bMaziyarPanahi · Fine-tune9.2K downloads
- Athene-70BNexusflow · Fine-tune3.5K downloads
- Meta-Llama-3-70B-Instruct-GGUF-v2QuantFactory · Quantization1.9K downloads
- Meta-Llama-3-70B-Instruct-GGUFQuantFactory · Quantization1.8K downloads
- Meta-Llama-3-120B-Instruct-GGUFbartowski · Quantization1.5K downloads
BenchClub runs
Not runnable yet
Runs open once a Meta-Llama-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