Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)
NVIDIALlamaOpen WeightLlama 3.1 Community License
Descripción
Llama-3.1-Nemotron-Nano-8B-v1 is a large language model (LLM) which is a derivative of Meta Llama-3.1-8B-Instruct (AKA the reference model). It is a reasoning model that is post trained for reasoning, human chat preferences, and tasks, such as RAG and tool calling.
Fecha de lanzamiento
2025-05-20
Parámetros
8.0B
Longitud del contexto
131K
Modalidades
text
Radar de capacidades
21
general
49
coding
61
reasoning
30
science
60
agents
0
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 456 | 27.0 | AA |
| Ranking general | 569 | 21.0 | AA |
| Ciencia | 551 | 22.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.81 / 100Aut.
IFEvalGoogle Research (2023)
79.3%Aut.
General
BFCL v2
63.6%Aut.
Math
MATH-500
95.4%Aut.
AIME 2025
47.1%Aut.
Reasoning
MBPP
0.85 / 100Aut.
GPQANYU + Cohere + Anthropic (2023)
54.1%Aut.
Índices de evaluación AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))94.7
Aime(MAA (Mathematical Association of America))70.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))55.6
Math Index(Artificial Analysis)50.0
Aime 25(MAA (Mathematical Association of America))50.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))49.3
Gpqa(NYU + Cohere + Anthropic (2023))40.8
Ifbench(Google Research (2023))25.5
Tau2(Sierra + U Toronto + Vector Institute (2025))11.7
Intelligence Index(Artificial Analysis)7.3
Hle(Center for AI Safety + Scale AI (2025))5.2
Lcr(Artificial Analysis)0.0
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Chat80
Instruction Following80
Roleplay80
Structured Output80
Communication80
Creativity80
Math70
Reasoning70
General70
Tool Calling60
Physics50
Biology50
Chemistry50
Precios
Precio de entradaGratis
Precio de salidaGratis
Precio mixto (3:1)Gratis
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
No hay datos de proveedores disponibles