跳轉到主要內容

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

NVIDIA開源權重NVIDIA Open Model License Agreement · 商用許可

描述

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.

發布日期
2025-08-18
參數規模
8.9B
上下文長度
131K
支援模態
text

能力雷達圖

27
general
59
coding
61
reasoning
33
science
60
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜311
36.0
AA
通用能力榜434
29.0
AA
科學能力414
32.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)64.0%自報

Code

LiveCodeBench71.1%自報

General

IFEvalGoogle Research (2023)90.3%自報
BFCL_v3_MultiTurn66.9%自報

Math

MATH-50097.8%自報
AIME 202572.1%自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
62.3
Intelligence Index(Artificial Analysis)
7.2
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.7
Aime 25(MAA (Mathematical Association of America))
0.6
Gpqa(NYU + Cohere + Anthropic (2023))
0.6
Ifbench(Google Research (2023))
0.3
Lcr(Artificial Analysis)
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Scicode(UIUC + Argonne National Lab (2024))
0.2
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分類評分

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

定價

輸入價格$0.05 / 1M tokens
輸出價格$0.195 / 1M tokens
混合價格(3:1)$0.086 / 1M tokens

速度

Tokens/秒166.7
首Token延遲1.33s
首回答延遲1.33s

供應商價格排行

供應商價格排行

1 個供應商

供應商輸入輸出
1NVIDIA主要
$0.05
$0.195

比較該模型在不同 API 供應商之間的定價。

外部連結