Hermes 3 - Llama-3.1 70B
Nous ResearchLlama开源权重Apache 2.0 · 商用许可
描述
Hermes 3 70B is Nous Research's flagship instruction-following model, fine-tuned for advanced reasoning, creative writing, and complex task completion. It features exceptional instruction adherence and strong performance across multiple domains.
发布日期
2024-08-15
参数规模
70.0B
上下文长度
131K
支持模态
text
能力雷达图
21
general
19
coding
25
reasoning
29
science
23
agents
0
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
8.99 / 100自报
General
MMLU
79.1%自报
TruthfulQA
63.3%自报
Instruction Following
IFBench
81.2%自报
Language
BoolQ
88.0%自报
MMLU-Pro
47.2%自报
Math
MATH
20.8%自报
Reasoning
HellaSwagAI2 (2019)
88.2%自报
PIQA
84.4%自报
Winogrande
83.2%自报
ARC-E
83.0%自报
BBH
67.8%自报
GPQANYU + Cohere + Anthropic (2023)
66.1%自报
ARC-C
65.5%自报
AGIEval
56.2%自报
MuSR
50.7%自报
OpenBookQA
49.4%自报
AA 评测指数
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))57.1
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))53.8
Gpqa(NYU + Cohere + Anthropic (2023))40.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))18.8
Intelligence Index(Artificial Analysis)6.0
Hle(Center for AI Safety + Scale AI (2025))4.0
Aime(MAA (Mathematical Association of America))2.3
LLM Stats 分类评分
(LLM Stats (zeroeval))Chat9
Roleplay9
Communication9
Creativity9
Reasoning1
General1
Instruction Following80
Physics80
Language70
Biology70
Chemistry70
Legal60
Finance60
Healthcare60
Math50
定价
输入价格$0.7 / 1M tokens
输出价格$0.7 / 1M tokens
混合价格(3:1)$0.7 / 1M tokens
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
供应商价格排行
4 个供应商
最便宜: DeepInfra最贵: Kilo Gateway
供应商输入输出
1DeepInfra最便宜
$0
$0
2Nous Research主要
$0.7
$0.7
3OpenRouter
$0.7
$0.7
4Kilo Gateway
$0.7
$0.7
比较该模型在不同 API 供应商之间的定价。