Hermes 3 - Llama-3.1 70B
Nous ResearchLlamaOpen WeightApache 2.0 · Commercial OK
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
24
general
20
coding
25
reasoning
27
science估算
0
agents
0
multimodal
Science 在缺少专门科学评测时使用推理能力代理估算。
排行榜排名
基准测试分数 (LLM Stats)
Biology
GPQA
66.1%自报
Communication
MT-Bench
8.99 / 100自报
Finance
MMLU
79.1%自报
TruthfulQA
63.3%自报
MMLU-Pro
47.2%自报
General
PIQA
84.4%自报
ARC-E
83.0%自报
IFBench
81.2%自报
ARC-C
65.5%自报
AGIEval
56.2%自报
OpenBookQA
49.4%自报
Language
BoolQ
88.0%自报
Winogrande
83.2%自报
BBH
67.8%自报
Math
MATH
20.8%自报
Reasoning
HellaSwag
88.2%自报
MuSR
50.7%自报
AA 评测指数
Intelligence Index10.6
Mmlu Pro0.6
Math 5000.5
Gpqa0.4
Scicode0.2
Livecodebench0.2
Hle0.0
Aime0.0
LLM Stats 分类评分
Communication9
Creativity9
Roleplay9
General1
Reasoning1
Instruction Following80
Physics80
Biology70
Chemistry70
Language70
Finance60
Healthcare60
Legal60
Math50
定价
输入价格$0.3 / 1M tokens
输出价格$0.3 / 1M tokens
混合价格(3:1)$0.3 / 1M tokens
速度
Tokens/秒30.6 tokens/s
首Token延迟0.46s
首回答延迟0.46s
可用提供商
(LS 内部计价单位)暂无提供商数据