Skip to main content

Llama 3.1 Instruct 8B

MetaLlamaOpen WeightLlama 3.1 Community License

Description

Llama 3.1 8B Instruct is a multilingual large language model optimized for dialogue use cases. It features a 128K context length, state-of-the-art tool use, and strong reasoning capabilities.

Release Date
2024-07-23
Parameters
8.0B
Context Length
131K
Modalities
text

Capability Radar

60
general
40
coding
60
reasoning
26
scienceest.
50
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)80.4%SR

General

BFCL76.1%SR
MMLU69.4%SR
Multipl-E MBPP52.4%SR
Nexus38.5%SR

Language

MMLU (CoT)73.0%SR
Multipl-E HumanEval50.8%SR
MMLU-Pro48.3%SR

Math

GSM-8K (CoT)84.5%SR
Multilingual MGSM (CoT)68.9%SR
MATH (CoT)51.9%SR

Reasoning

ARC-C83.4%SR
API-Bank82.6%SR
MBPP EvalPlus (base)72.8%SR
HumanEvalOpenAI (2021)72.6%SR
DROP59.5%SR
GPQANYU + Cohere + Anthropic (2023)30.4%SR
Gorilla Benchmark API Bench8.2%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Chat
80
Instruction Following
80
Structured Output
80
Language
60
Legal
60
Math
60
Reasoning
60
Finance
60
General
60
Healthcare
60
Tool Calling
50
Code
40
Physics
30
Biology
30
Chemistry
30

Pricing

Input Price$0.035 / 1M tokens
Output Price$0.065 / 1M tokens
Blended Price (3:1)$0.025 / 1M tokens

Speed

Tokens/sec141.3
Time to First Token0.87s
Time to Answer0.87s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: DeepInfraMost Expensive: Meta
ProviderInputOutput
1DeepInfraCheapest
$0.02
$0.04
2MetaPRIMARY
$0.035
$0.065

Compare pricing across different API providers for this model.

External Sources