Skip to main content
AITier

Llama 3.1 Instruct 70B

MetaLlamaOpen WeightLlama 3.1 Community License

Description

Llama 3.1 70B Instruct is a large language model optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common industry benchmarks.

Release Date
2024-07-23
Parameters
70.0B
Context Length
131K
Modalities
text

Capability Radar

28
general
17
coding
20
reasoning
29
scienceest.
70
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking385
15.0
AA
General Ranking367
30.0
AA
Math Reasoning306
19.0
AA
Reasoning10
90.0
LS
Science357
30.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA41.7%SR

Code

HumanEval80.5%SR
Gorilla Benchmark API Bench29.7%SR

Finance

MMLU (CoT)86.0%SR
MMLU83.6%SR
MMLU-Pro66.4%SR

General

ARC-C94.8%SR
IFEval87.5%SR
MBPP ++ base version86.0%SR
BFCL84.8%SR
Multipl-E HumanEval65.5%SR
Multipl-E MBPP62.0%SR
Nexus56.7%SR

Math

GSM-8K (CoT)95.1%SR
Multilingual MGSM (CoT)86.9%SR
DROP79.6%SR
MATH (CoT)68.0%SR

Reasoning

API-Bank90.0%SR

AA Evaluation Indices

Intelligence Index
12.5
Coding Index
10.9
Math Index
4.0
Mmlu Pro
0.7
Math 500
0.6
Gpqa
0.4
Ifbench
0.3
Scicode
0.3
Livecodebench
0.2
Aime
0.2
Tau2
0.2
Lcr
0.1
Hle
0.0
Aime 25
0.0
Terminalbench Hard
0.0

LLM Stats Category Scores

Structured Output
90
Instruction Following
90
Finance
80
Healthcare
80
Language
80
Legal
80
Math
80
Tool Calling
70
General
70
Reasoning
70
Code
60
Biology
40
Chemistry
40
Physics
40

Pricing

Input Price$0.56 / 1M tokens
Output Price$0.56 / 1M tokens
Blended Price (3:1)$0.56 / 1M tokens

Speed

Tokens/sec33.0 tokens/s
Time to First Token0.62s
Time to Answer0.62s

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats