Llama 3.1 Instruct 405B
MetaLlama开源权重Llama 3.1 Community License
描述
Llama 3.1 405B Instruct is a large language model optimized for multilingual dialogue use cases. It outperforms many available open source and closed chat models on common industry benchmarks. The model supports 8 languages and has a 128K token context length.
发布日期
2024-07-23
参数规模
405.0B
上下文长度
—
支持模态
text
能力雷达图
27
general
30
coding
23
reasoning
34
science
70
agents
0
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
50.7%自报
Code
HumanEvalOpenAI (2021)
89.0%自报
Gorilla Benchmark API Bench
35.3%自报
Finance
MMLU (CoT)
88.6%自报
MMLU
87.3%自报
MMLU-Pro
73.3%自报
General
ARC-C
96.9%自报
MBPP EvalPlus
88.6%自报
IFEvalGoogle Research (2023)
88.6%自报
BFCL
88.5%自报
Multipl-E HumanEval
75.2%自报
Multipl-E MBPP
65.7%自报
Nexus
58.7%自报
Math
GSM8k
96.8%自报
Multilingual MGSM (CoT)
91.6%自报
DROP
84.8%自报
MATH
73.8%自报
Reasoning
API-Bank
92.0%自报
AA 评测指数
(Artificial Analysis)Intelligence Index(Artificial Analysis)8.3
Math Index(Artificial Analysis)3.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.7
Gpqa(NYU + Cohere + Anthropic (2023))0.5
Ifbench(Google Research (2023))0.4
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.3
Scicode(UIUC + Argonne National Lab (2024))0.3
Lcr(Artificial Analysis)0.2
Aime(MAA (Mathematical Association of America))0.2
Tau2(Sierra + U Toronto + Vector Institute (2025))0.2
Terminalbench Hard(Stanford × Laude Institute (2026))0.1
Hle(Center for AI Safety + Scale AI (2025))0.0
Aime 25(MAA (Mathematical Association of America))0.0
LLM Stats 分类评分
(LLM Stats (zeroeval))Math90
Structured Output90
Instruction Following90
Legal80
Reasoning80
Language80
Finance80
General80
Healthcare80
Tool Calling70
Code60
Physics50
Biology50
Chemistry50
定价
输入价格免费
输出价格免费
混合价格(3:1)免费
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
暂无提供商数据