Claude 3 Haiku
AnthropicClaudeProprietary
描述
Claude 3 Haiku is the fastest and most compact model in the Claude 3 family, designed for near-instant responsiveness. It excels at answering simple queries and requests with unmatched speed, making it ideal for seamless AI experiences that mimic human interactions.
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
5
general
15
coding
20
reasoning
27
science
19
agents
80
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))General
MMLU
75.2%自报
Math
GSM8k
88.9%自报
MGSM
75.1%自报
MATH
38.9%自报
Reasoning
ARC-C
89.2%自报
HellaSwagAI2 (2019)
85.9%自报
DROP
78.4%自报
HumanEvalOpenAI (2021)
75.9%自报
BIG-Bench Hard
73.7%自报
GPQANYU + Cohere + Anthropic (2023)
33.3%自报
AA 评测指数
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))39.4
Gpqa(NYU + Cohere + Anthropic (2023))37.4
Ifbench(Google Research (2023))36.1
Lcr(Artificial Analysis)27.7
Tau2(Sierra + U Toronto + Vector Institute (2025))21.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))15.4
Intelligence Index(Artificial Analysis)5.6
Hle(Center for AI Safety + Scale AI (2025))4.1
Aime(MAA (Mathematical Association of America))1.0
Terminalbench Hard(Stanford × Laude Institute (2026))0.8
LLM Stats 分类评分
(LLM Stats (zeroeval))Legal80
Finance80
Healthcare80
Code80
Language70
Math70
Reasoning70
General70
Physics30
Biology30
Chemistry30
定价
输入价格$0.25 / 1M tokens
输出价格$1.25 / 1M tokens
混合价格(3:1)$0.5 / 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
1 个供应商
供应商输入输出
1Anthropic主要
$0.25
$1.25
比较该模型在不同 API 供应商之间的定价。