Passer au contenu principal

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

NVIDIAOpen WeightNVIDIA Open Model License Agreement · Usage Commercial

Description

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so, albeit with a slight decrease in accuracy for harder prompts that require reasoning. Conversely, allowing the model to generate reasoning traces first generally results in higher-quality final solutions to queries and tasks.

Date de sortie
2025-08-18
Paramètres
8.9B
Longueur du contexte
131K
Modalités
text

Radar de capacités

27
general
70
coding
61
reasoning
40
science
64
agents
0
multimodal

Classements

Domaine#RangScoreSource
Classement codage389
35.0
AA
Classement général498
28.0
AA
Science465
30.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)90.3%Aut.

General

BFCL_v3_MultiTurn66.9%Aut.

Math

MATH-50097.8%Aut.
AIME 202572.1%Aut.

Reasoning

LiveCodeBench71.1%Aut.
GPQANYU + Cohere + Anthropic (2023)64.0%Aut.

Indices d'évaluation AA

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
73.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))
70.1
Aime 25(MAA (Mathematical Association of America))
62.3
Math Index(Artificial Analysis)
62.3
Gpqa(NYU + Cohere + Anthropic (2023))
55.7
Ifbench(Google Research (2023))
27.1
Lcr(Artificial Analysis)
24.0
Tau2(Sierra + U Toronto + Vector Institute (2025))
23.4
Intelligence Index(Artificial Analysis)
6.8
Hle(Center for AI Safety + Scale AI (2025))
4.6
Terminalbench Hard(Stanford × Laude Institute (2026))
0.8

Scores par catégorie LLM Stats

(LLM Stats (zeroeval))
Chat
90
Instruction Following
90
Structured Output
90
Math
80
Reasoning
80
General
80
Code
70
Physics
60
Biology
60
Chemistry
60

Tarification

Prix d'entrée$0.05 / 1M tokens
Prix de sortie$0.195 / 1M tokens
Prix mixte (3:1)$0.086 / 1M tokens

Vitesse

Tokens/sec161.6
Délai du premier token1.16s
Temps de réponse1.16s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

1 fournisseurs

FournisseurEntréeSortie
1NVIDIAPRINCIPAL
$0.05
$0.195

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes