← LLM ModelsOpen SourceView on HF →
Llama 3.3 70B Instruct (free)
Meta
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
openrouter.ai ↗📖Context131K tokens
🚀Speed-
💵Input price$0.100/1M
💸Output price$0.320/1M
🧠Parameters70.554B
Benchmarks
Gray bar = dataset averageComposite ScoreScore = MMLU×20% + GPQA×30% + HumanEval×25% + SWE-Bench×25%-
HF Open LLM Leaderboard
IFEval · BBH · MATH · GPQA · MuSR · MMLU-Pro
Average
44.9
IFEvalInstruction following
90.0%avg 79.9
BBHBig Bench Hard
56.6%avg 48.7
MATH Lvl 5Competition mathematics
48.3%avg 37.8
GPQAGraduate-level science Q&A
10.5%avg 12.9
MuSRMultistep soft reasoning
15.6%avg 10.7
MMLU-ProProfessional knowledge
48.1%avg 40.0
More from Meta
API Providers
Details
- Provider
- Meta
- Parameters
- 70.554B
- Context
- 131K tokens
- Speed
- -
- Open Source
- Yes
- License
- Open (varies)
- Released
- Dec 2024