NVIDIA Llama 3.1 Nemotron 70B：完整基准性能指南

other nvidia-llama-3-1-nemotron-70b 2024-10-17 Llama 3.1 Community License

深入分析 NVIDIA Llama 3.1 Nemotron 70B 在 MMLU、HumanEval、GSM8K、MATH、BBH 等基准上的表现，包含定价与适用场景。

Key Specifications

Vendorother
Versionnvidia-llama-3-1-nemotron-70b
Release Date2024-10-17
Context Window131072 tokens
Input Modalitiestext
Output Modalitiestext
LicenseLlama 3.1 Community License
Documentationhttps://huggingface.co/models

Benchmark Performance

BenchmarkScoreUnitEvaluated AtNotesSource
MMLU80.4%2024-10-175-shotview
HUMANEVAL66.4pass@12024-10-17—view
GSM8K77.8%2024-10-170-shot CoTview
MATH40.3%2024-10-170-shot CoTview
BBH76.6%2024-10-173-shot CoTview
GPQA37.6%2024-10-170-shotview
IFEVAL69.6%2024-10-17prompt_strictview
ARC93.2%2024-10-17challengeview
MUSR47.7%2024-10-170-shotview
WINOGRANDE84.7%2024-10-170-shotview

Pricing

TierPriceCurrency
Input$0.9 / MtokUSD
Output$0.9 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-10-17

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

NVIDIA Llama 3.1 Nemotron 70B

模型概述

NVIDIA Llama 3.1 Nemotron 70B, 131K 上下文, NVIDIA 优化 Llama 3.1, 在 Arena 上接近 GPT-4o。

核心规格

厂商版本发布日期上下文窗口输入模态输出模态许可证
Othernvidia-llama-3-1-nemotron-70b2024-10-17131KtexttextLlama 3.1 Community License

基准测试表现

基准得分单位备注
MMLU (Massive Multitask Language Understanding)80.4%5-shot
HumanEval66.4pass@1—
GSM8K (Grade School Math 8K)77.8%0-shot CoT
MATH40.3%0-shot CoT
BBH (BIG-Bench Hard)76.6%3-shot CoT
GPQA37.6%0-shot
IFEval69.6%prompt_strict
ARC93.2%challenge
MUSR47.7%0-shot
WinoGrande84.7%0-shot

定价

输入输出缓存读取缓存写入
————

每百万 token

优势

  • MMLU 得分 80.4，知识推理能力强。

劣势

  • 闭源专有模型，不支持自托管。

适用场景

  • 通用对话与问答

参考文献