MetaLlama 3Open SourceArena #195Apr 18, 2024

Meta: Llama 3 70B Instruct

Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy.

Context Window
8K
tokens
Max Output
8K
tokens
Released
Apr 18, 2024
Arena Rank
#195
of 305 models

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
⚡Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Repetition Penalty
Penalize repeated tokens
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouter$0.51$0.74—
Martian$0.51$0.74—

Benchmarks

Open LLM Leaderboard
AverageOpen LLM Leaderboard
36.37/100
IFEvalOpen LLM Leaderboard
80.99/100
BBHOpen LLM Leaderboard
50.19/100
MATH Lvl 5Open LLM Leaderboard
24.47/100
GPQAOpen LLM Leaderboard
4.92/100
MUSROpen LLM Leaderboard
10.92/100
MMLU-PROOpen LLM Leaderboard
46.74/100

Model IDs

OpenRoutermeta-llama/llama-3-70b-instruct
Hugging Facemeta-llama/Meta-Llama-3-70B-Instruct ↗
Compare with another model

Related Models

Meta#225

Meta: Llama 3 8B Instruct

8K ctx$0.03/1M in
Meta#258

Meta: Llama 3.2 3B Instruct (free)

131K ctxFree/1M in
Meta#287

Meta: Llama 3.2 1B Instruct

60K ctx$0.03/1M in
Meta

Meta Llama 3 8B Instruct Lite

8K ctx$0.10/1M in
Meta

Llama 3.2 3B Instruct Turbo

131K ctx$0.06/1M in
Meta

Llama 3.2 90B Vision Instruct

131K ctx$0.35/1M in
← Back to all models