Claude 3.5 Haiku
AnthropicClaudeProprietary
描述
Claude 3.5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price. It excels at user-facing products, specialized sub-agent tasks, and generating personalized experiences from large data volumes. The model is particularly well-suited for code completions, interactive chatbots, data extraction, and real-time content moderation.
发布日期
2024-10-22
参数规模
—
上下文长度
200K
支持模态
image, text
能力雷达图
30
general
20
coding
31
reasoning
29
science估算
40
agents
80
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
41.6%自报
Code
HumanEval
88.1%自报
SWE-Bench Verified
40.6%自报
Communication
TAU-bench Retail
51.0%自报
TAU-bench Airline
22.8%自报
Finance
MMLU-Pro
65.0%自报
Math
MGSM
85.6%自报
DROP
83.1%自报
MATH
69.4%自报
AA 评测指数
Intelligence Index18.7
Coding Index10.7
Math 5000.7
Mmlu Pro0.6
Ifbench0.4
Gpqa0.4
Livecodebench0.3
Scicode0.3
Tau20.2
Lcr0.2
Hle0.0
Aime0.0
Terminalbench Hard0.0
LLM Stats 分类评分
Math80
Finance70
Healthcare70
Language70
Legal70
Code60
Reasoning60
General50
Tool Calling40
Biology40
Chemistry40
Communication40
Frontend Development40
Physics40
定价
输入价格$1 / 1M tokens
输出价格$4 / 1M tokens
混合价格(3:1)$1.75 / 1M tokens
速度
Tokens/秒0.0 tokens/s
首Token延迟0.00s
首回答延迟0.00s
可用提供商
(LS 内部计价单位)暂无提供商数据