跳转到主要内容

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

NVIDIALlama开源权重Llama 3.1 Community License

描述

A 253B parameter derivative of Meta Llama 3.1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression. It underwent multi-phase post-training (SFT for Math, Code, Reasoning, Chat, Tool Calling; RL with GRPO) to enhance reasoning and instruction-following. Optimized for accuracy/efficiency tradeoff on NVIDIA GPUs. Supports 128k context.

发布日期
2025-04-07
参数规模
253.0B
上下文长度
128K
支持模态
text

能力雷达图

31
general
58
coding
72
reasoning
46
science
70
agents
0
multimodal

排行榜排名

领域#排名分数来源
代码能力榜371
27.0
AA
通用能力榜385
33.0
AA
科学能力258
48.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)76.0%自报

Code

LiveCodeBench66.3%自报

General

IFEvalGoogle Research (2023)89.5%自报
BFCL v274.1%自报

Math

MATH-50097.0%自报
AIME 202572.5%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
63.7
Intelligence Index(Artificial Analysis)
8.9
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Aime(MAA (Mathematical Association of America))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.6
Aime 25(MAA (Mathematical Association of America))
0.6
Ifbench(Google Research (2023))
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Lcr(Artificial Analysis)
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分类评分

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

定价

输入价格$0.6 / 1M tokens
输出价格$1.8 / 1M tokens
混合价格(3:1)$0.9 / 1M tokens

速度

Tokens/秒53.0
首Token延迟0.68s
首回答延迟38.40s

供应商价格排行

供应商价格排行

1 个供应商

供应商输入输出
1NVIDIA主要
$0.6
$1.8

比较该模型在不同 API 供应商之间的定价。

外部链接