RSS

Meta

Llama 3.3 70B Instruct

Benchmarks, price, context and versions

Also searched as

Llama-3.3-70B-Instruct

Direct answer: Llama 3.3 70B Instruct is a model from Meta. 49.8% on GPQA Diamond (OpenRouter), per OpenRouter Benchmarks. On OpenRouter, US$ 0.71 per 1 million input tokens and US$ 0.71 per 1 million output tokens.

✓ Good for

  • running on your own infrastructure (open weights)

✕ Not the best for

  • technical reasoning as the model appears through the API (#126 of 135 on GPQA Diamond (OpenRouter))
  • agents that follow rules and use tools (#126 of 131 on τ-bench Verified (airline))

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

τ-bench Verified (airline)

?
39.9%

highest score on this metric 82%

126º / 131 · OpenRouter Benchmarks, latest version we checked

Key specs

Lab
Meta
Origin
the US
Family
Llama Instruct provisional data
Weights?
open
License
llama3.3
Input US$/1M?
US$ 0.71
Output US$/1M
US$ 0.71
Context?
131,072 tokens
Parameters
70,553,706,496
Input
text
OpenRouter usage?
no data
Downloads (30 days)?
349,408
Use cases provisional data
Text Agents
Dates in sources
  • 2024, listed on OpenRouter
  • 2024, Hugging Face repo created

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

What is Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct is a model from Meta, with open weights, used for text, agents.

How much does Llama 3.3 70B Instruct cost?

On OpenRouter, US$ 0.71 per 1 million input tokens and US$ 0.71 per 1 million output tokens.

What is the context window of Llama 3.3 70B Instruct?

131,072 tokens, per OpenRouter.

Is Llama 3.3 70B Instruct open source?

Yes, it has open weights. License: llama3.3.

What is Llama 3.3 70B Instruct's GPQA Diamond (OpenRouter) score?

49.8% on GPQA Diamond (OpenRouter), per OpenRouter Benchmarks.

Is Llama 3.3 70B Instruct good for coding?

No data: there is no SWE-bench Verified measurement for it in open sources.

Who made Llama 3.3 70B Instruct?

It was made by Meta, a lab from the US.

provisional data Questions under review: Semrush had no API balance during collection. Answers use source data only.

Models from Meta

See lab

Sources

  • Hugging Face Hub, metadados públicos do Hub; licença de cada modelo no repositório, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.