Skip to content

Meta · Chat

Meta Llama 3 70b

Meta 🇺🇸ChatLlama family

Newer version: Llama 3.1 70B. We compared release dates and version names in our catalogue.

From Replicate's listing:
Base version of Llama 3, a 70 billion parameter language model from Meta.
llminfo IQ
106.1
Market median price
$0.64 blended / 1M
Max context
8K
Listings
7

Evidence and sources

llminfo IQ 106.1, ranked among chat models. From 92 benchmarks. Plenty of data behind it.How llminfo IQ is computedPoor value (39.8). Costs more per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 18 Apr 2024Maker HQ: US (according to Meta's own website)
Sources: Helicone Costs data, Replicate data docs, llminfo researchPrimary data from Helicone Costs from Replicate: name, description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Text

Listings

 Aihubmixmeta-llama-3-70bSource: AIHubMix data docsNot published by the provider$4.795$4.795
 Replicatemeta/meta-llama-3-70bSources: LiteLLM data, Replicate data docs8K$0.65$2.75
 Vercelmeta/llama-3-70bSource: Helicone Costs dataNot published by the provider$0.59$0.79
 Vercel AI Gatewayvercel_ai_gateway/meta/llama-3-70bSource: LiteLLM data8K$0.59$0.79

3 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Knowledge

HELM59 related benchmarks · 59 results
Show 53 more resultsHide 53 results

Multilingual

SeaLLMs SeaExamSource: SeaLLMs Leaderboard for SEA Languages data docs

Reasoning

General

Math

Science

Factuality

Instruction following

Other

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM), Apache-2.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Hugging Face official benchmark leaderboards; licence varies by benchmark · pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence) · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated.

Around the web

Also known as: llama3:70b, meta-llama-3-70b, meta/llama-3-70b, meta/meta-llama-3-70b, ollama/llama3:70b, replicate/meta/llama-3-70b, replicate/meta/meta-llama-3-70b, snowflake/llama3-70b, vercel_ai_gateway/meta/llama-3-70b

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works