Claude 3 Sonnet
AnthropicClaudeProprietary
描述
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
发布日期
2024-03-04
参数规模
—
上下文长度
—
支持模态
image, text
能力雷达图
21
general
18
coding
23
reasoning
29
science
21
agents
80
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
79.0%自报
Language
MMLU-Pro
56.8%自报
Math
GSM8k
92.3%自报
MGSM
83.5%自报
MATH
43.1%自报
Reasoning
ARC-C
93.2%自报
HellaSwagAI2 (2019)
89.0%自报
BIG-Bench Hard
82.9%自报
DROP
78.9%自报
HumanEvalOpenAI (2021)
73.0%自报
GPQANYU + Cohere + Anthropic (2023)
40.4%自报
AA 评测指数
(Artificial Analysis)Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))57.9
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))41.4
Gpqa(NYU + Cohere + Anthropic (2023))40.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))17.5
Intelligence Index(Artificial Analysis)5.9
Aime(MAA (Mathematical Association of America))4.7
Hle(Center for AI Safety + Scale AI (2025))3.6
LLM Stats 分类评分
(LLM Stats (zeroeval))Language70
Legal70
Math70
Reasoning70
Finance70
General70
Healthcare70
Code70
Physics40
Biology40
Chemistry40
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