DataLearner logo
LL

Llama3.1-70B-Instruct

Foundation modelLlama3.1

Llama3.1-70B-Instruct

Release date: 2024-07-23Updated: 2024-07-24Views: 629
Parameters
70B
Context length
128K
Multilingual
No data
Reasoning ability
No data

Llama3.1-70B-Instruct is an AI model published by Facebook AI Research Lab, released on 2024-07-23, for Foundation model, with 70B parameters, and 128K context length, requiring about 140GB storage, with a 781.90 score on Creative Writing.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Llama3.1-70B-Instruct

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Foundation model
Modality (in / out)
No data
Release date
2024-07-23
Model file size
140GB
MoE architecture
No
Total params / Active params
70B / Not applicable
Knowledge cutoff
No data
Llama3.1-70B-Instruct

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
N/A
Llama3.1-70B-Instruct

Official resources

Paper
N/A
DataLearnerAI blog
Llama3.1-70B-Instruct

API details

API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.400/ 1M tokens$0.400/ 1M tokens

“—” means the modality is not billed in that direction, or the vendor has not published a price for it.

Llama3.1-70B-Instruct

Benchmark Results

Llama3.1-70B-Instruct currently shows benchmark results led by MBPP (9 / 96, score 86), MMLU (35 / 124, score 86), HumanEval (41 / 140, score 80.50). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
Tool usage

General Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Standard Mode
86
35 / 124
MMLU Pro
Standard Mode
66.40
111 / 176
MMLU Pro
unknown
62.84
119 / 176

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
MBPP
Standard Mode
86
9 / 96
HumanEval
Standard Mode
80.50
41 / 140
LiveCodeBench
Standard Mode
33.30
206 / 250
WeirdML v2
Standard ModeTools
8.97
52 / 52

Math and Reasoning

1 evaluations
Benchmark / mode
Score
Rank/total
MATH
Standard Mode
67.80
26 / 42

General Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
48
415 / 462

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
781.90
96 / 106

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
BALROG
Standard ModeTools
27.90
11 / 12

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
10.70
44 / 45
Llama3.1-70B-Instruct

Publisher

Facebook AI Research Lab
Facebook AI Research Lab
View publisher details
Llama3.1-70B-Instruct

Model Overview

Llama3.1-70B-Instruct is an AI model published by Facebook AI Research Lab, released on 2024-07-23, for Foundation model, with 70B parameters, and 128K context length, requiring about 140GB storage, with a 781.90 score on Creative Writing.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code