Llama 3 70B
LegacyMeta's original Llama 3 70B instruction model. Strong open-weight model at its release. Superseded by Llama 3.1 and 3.3 70B.
Benchmarks
This model hasn't been evaluated by Artificial Analysis yet. Benchmark scores will appear once they're published.
Specifications
Providers
Compare with
GPT 6 Astravs Llama 3 70BGPT 6.1 Sol Provs Llama 3 70BGPT 6.1 Solvs Llama 3 70BGPT 6 Lunavs Llama 3 70B
Claude Fable 5.1vs Llama 3 70BClaude Opus 5.5vs Llama 3 70BClaude Sonnet 5.5vs Llama 3 70B
Gemini 3.8 Flashvs Llama 3 70BGemini 4 Argonvs Llama 3 70BGemma 4 31Bvs Llama 3 70B
Grok 4.7vs Llama 3 70BGrok Build 0.1vs Llama 3 70B
Muse Spark Openvs Llama 3 70BMuse Wondervs Llama 3 70B
DeepSeek V4 Pro (0813)vs Llama 3 70BDeepSeek V4.1 Flash 1017vs Llama 3 70B
MiniMax M3vs Llama 3 70B
Kimi K3vs Llama 3 70BKimi K2.7 Codevs Llama 3 70B
GLM 5.3vs Llama 3 70BGLM 5.3 Flashvs Llama 3 70B
Qwen3.8 Max (0902)vs Llama 3 70BQwen3 Coder Nextvs Llama 3 70B
Nemotron 3 Ultravs Llama 3 70BNemotron 3.5 Super VLvs Llama 3 70BFrequently Asked Questions about Llama 3 70B▼
Who created Llama 3 70B?
▼
Llama 3 70B was created by Meta.
Is Llama 3 70B a reasoning model?
▼
No, Llama 3 70B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.
Does Llama 3 70B support image or vision input?
▼
No, Llama 3 70B does not currently support image or vision input. It is a text-only model.
Does Llama 3 70B support audio?
▼
No, Llama 3 70B does not support audio input.
What is the context window of Llama 3 70B?
▼
Llama 3 70B has a context window of 8K tokens, meaning it can process approximately 6,144 words of context at once.
Is Llama 3 70B open source?
▼
Llama 3 70B is a proprietary model developed by Meta. The model weights and training data are not publicly available.
Where can I use Llama 3 70B?
▼
You can chat with Llama 3 70B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Llama 3 70B through Meta's own API or platform.