Saltar al contenido principal

Llama 3.3 Instruct 70B

MetaLlamaOpen WeightLlama 3.3 Community License Agreement

Descripción

Llama 3.3 is a multilingual large language model optimized for dialogue use cases across multiple languages. It is a pretrained and instruction-tuned generative model with 70 billion parameters, outperforming many open-source and closed chat models on common industry benchmarks. Llama 3.3 supports a context length of 128,000 tokens and is designed for commercial and research use in multiple languages.

Fecha de lanzamiento
2024-12-06
Parámetros
70.0B
Longitud del contexto
131K
Modalidades
text

Radar de capacidades

27
general
19
coding
28
reasoning
32
science
80
agents
0
multimodal

Rankings

Dominio#PosiciónPuntuaciónFuente
Ranking de codificación438
17.0
AA
Ranking general344
36.0
AA
Ciencia404
32.0
AA

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)50.5%Aut.

Code

HumanEvalOpenAI (2021)88.4%Aut.

Finance

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

General

IFEvalGoogle Research (2023)92.1%Aut.
MBPP EvalPlus87.6%Aut.
BFCL v277.3%Aut.

Math

MGSM91.1%Aut.
MATH77.0%Aut.

Índices de evaluación AA

(Artificial Analysis)
Coding Index(Artificial Analysis)
11.9
Intelligence Index(Artificial Analysis)
9.3
Math Index(Artificial Analysis)
7.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Ifbench(Google Research (2023))
0.5
Aime(MAA (Mathematical Association of America))
0.3
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.3
Scicode(UIUC + Argonne National Lab (2024))
0.3
Lcr(Artificial Analysis)
0.2
Aime 25(MAA (Mathematical Association of America))
0.1
Terminalbench V2 1
0.0
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

Puntuaciones por categoría LLM Stats

(LLM Stats (zeroeval))
Instruction Following
90
Structured Output
90
Code
90
Language
80
Legal
80
Math
80
Reasoning
80
Finance
80
General
80
Healthcare
80
Tool Calling
80
Physics
50
Biology
50
Chemistry
50

Precios

Precio de entrada$0.655 / 1M tokens
Precio de salida$0.72 / 1M tokens
Precio mixto (3:1)$0.671 / 1M tokens

Velocidad

Tokens/seg80.7
Retraso del primer token0.67s
Tiempo hasta la respuesta0.67s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

5 proveedores

Más barato: NanoGPTMás caro: Meta
ProveedorEntradaSalida
1NanoGPTMás barato
$0.05
$0.23
2OpenRouter
$0.1
$0.32
3Kilo Gateway
$0.1
$0.32
4NovitaAI
$0.135
$0.4
5MetaPRINCIPAL
$0.655
$0.72

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas