Skip to main content

Llama 3 Instruct 70B

MetaLlama
Release Date
2024-04-18
Parameters
Context Length
131K
Modalities
text

Capability Radar

20
general
20
coding
22
reasoning
25
scienceest.
80
agents
0
multimodal

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

Rankings

Domain#RankScoreSource
Code Ranking463
7.0
AA
General Ranking445
21.0
AA
Math Reasoning295
23.0
AA
Science421
23.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA50.5%SR

Code

HumanEval88.4%SR

Finance

MMLU86.0%SR
MMLU-Pro68.9%SR

General

IFEval92.1%SR
MBPP EvalPlus87.6%SR
BFCL v277.3%SR

Math

MGSM91.1%SR
MATH77.0%SR

AA Evaluation Indices

Intelligence Index
3.5
Mmlu Pro
0.6
Math 500
0.5
Gpqa
0.4
Ifbench
0.4
Livecodebench
0.2
Scicode
0.2
Hle
0.0
Terminalbench Hard
0.0
Aime
0.0
Lcr
0.0
Tau2
0.0

LLM Stats Category Scores

Instruction Following
90
Structured Output
90
Code
90
Language
80
Legal
80
Math
80
Reasoning
80
Finance
80
Healthcare
80
Tool Calling
80
General
70
Physics
50
Biology
50
Chemistry
50

Pricing

Input Price$0.65 / 1M tokens
Output Price$2.75 / 1M tokens
Blended Price (3:1)$1.175 / 1M tokens

Speed

Tokens/sec43.0
Time to First Token0.71s
Time to Answer0.71s

Provider Price Ranking

Provider Price Ranking

7 providers

Cheapest: NovitaAIMost Expensive: Azure
ProviderInputOutput
1NovitaAICheapest
$0.51
$0.74
2Kilo Gateway
$0.51
$0.74
3LLM Gateway
$0.51
$0.74
4MetaPRIMARY
$0.65
$2.75
5NanoGPT
$0.7
$0.7
6Azure Cognitive Services
$2.68
$3.54
7Azure
$2.68
$3.54

Compare pricing across different API providers for this model.

External Sources