Meta: Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instructThe 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...
Input modalitiesT
Output modalitiesT
Source-linkedClosed weights
Context window131.072K
Maximum output16.384K
Provider offers0
Knowledge cutoffUndisclosed
CapabilitiesWhat this model supports
- Creator
- Meta
- Family
- Not documented
- Modalities
- Text
- License
- Not documented
- Release date
- Not documented
- Model ID
meta-llama/llama-3.3-70b-instruct
No known providers available.
EvidencePublished benchmark results
Anthropic: Claude Opus 4.8
47.2
Meta: Llama 3.3 70B Instruct
0.3
Anthropic: Claude Opus 4.8
74.3
Anthropic: Claude Opus 4.7
73.6
Meta: Llama 3.3 70B Instruct
11.9
Anthropic: Claude Opus 4.8
55.7
Anthropic: Claude Opus 4.7
53.5
Meta: Llama 3.3 70B Instruct
9.4
