跳转到主要内容

Llama 3.1 Nemotron Instruct 70B

NVIDIALlama开源权重Llama 3.1 Community License

描述

A large language model customized by NVIDIA to improve the helpfulness of LLM generated responses. It is a fine-tuned version of Llama 3.1 70B Instruct. The model was trained using RLHF (REINFORCE) with HelpSteer2-Preference prompts.

发布日期
2024-10-15
参数规模
70.0B
上下文长度
128K
支持模态
text

能力雷达图

25
general
18
coding
27
reasoning
30
science
24
agents
0
multimodal

排行榜排名

领域#排名分数来源
代码能力榜498
11.0
AA
通用能力榜433
29.0
AA
科学能力440
29.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Communication

MT-Bench0.09 / 100自报

Finance

MMLU Chat80.6%自报
MMLU80.2%自报
TruthfulQA58.6%自报

General

Instruct HumanEval73.8%自报
ARC-C69.2%自报

Language

Winogrande84.5%自报
XLSum English31.6%自报

Math

GSM8k91.4%自报
GSM8K Chat81.9%自报

Reasoning

HellaSwagAI2 (2019)85.6%自报

AA 评测指数

(Artificial Analysis)
Math Index(Artificial Analysis)
11.0
Intelligence Index(Artificial Analysis)
7.4
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.7
Gpqa(NYU + Cohere + Anthropic (2023))
0.5
Ifbench(Google Research (2023))
0.3
Aime(MAA (Mathematical Association of America))
0.2
Scicode(UIUC + Argonne National Lab (2024))
0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.2
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.2
Aime 25(MAA (Mathematical Association of America))
0.1
Lcr(Artificial Analysis)
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0
Hle(Center for AI Safety + Scale AI (2025))
0.0

LLM Stats 分类评分

(LLM Stats (zeroeval))
Math
90
Language
80
Legal
70
Reasoning
70
Finance
70
General
70
Healthcare
70
Roleplay
10
Communication
10
Creativity
10

定价

输入价格$1.2 / 1M tokens
输出价格$1.2 / 1M tokens
混合价格(3:1)$1.2 / 1M tokens

速度

Tokens/秒82.3
首Token延迟5.52s
首回答延迟5.52s

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
$1.2
$1.2

比较该模型在不同 API 供应商之间的定价。

外部链接