Claude 4.5 Haiku (Non-reasoning)
AnthropicClaudeProprietary
描述
Claude Haiku 4.5 is Anthropic's fastest, most cost-efficient model, matching Sonnet 4's performance on coding, computer use, and agent tasks. It offers similar performance to Sonnet 4 at one-third the cost and more than twice the speed, making it ideal for high-volume, latency-sensitive applications and multi-agent orchestration.
發布日期
2025-10-15
參數規模
—
上下文長度
200K
支援模態
image, text
能力雷達圖
42
general
38
coding
43
reasoning
42
science估算
80
agents
80
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Agents
OSWorld
50.7%自報
Terminal-Bench
41.0%自報
Biology
GPQA
73.0%自報
Code
SWE-Bench Verified
73.3%自報
Communication
Tau2 Retail
83.2%自報
Tau2 Telecom
83.0%自報
Tau2 Airline
63.6%自報
General
MMMLU
83.0%自報
MMMU (validation)
73.2%自報
Math
AIME 2025
80.7%自報
Safety
Cybersecurity CTFs
46.9%自報
AA 評測指數
Math Index39.0
Intelligence Index31.1
Coding Index29.6
Mmlu Pro0.8
Gpqa0.6
Livecodebench0.5
Lcr0.4
Ifbench0.4
Aime 250.4
Scicode0.3
Tau20.3
Terminalbench Hard0.3
Hle0.0
LLM Stats 分類評分
Tool Calling80
Communication80
Language80
Math80
Biology70
Chemistry70
Frontend Development70
General70
Physics70
Reasoning70
Vision60
Code60
Multimodal60
Agents50
Healthcare50
Safety50
Long Context20
定價
輸入價格$1.25 / 1M tokens
輸出價格$5 / 1M tokens
混合價格(3:1)$2.188 / 1M tokens
速度
Tokens/秒121.7 tokens/s
首Token延遲0.52s
首回答延遲0.52s
可用提供商
(LS 內部計價單位)| 提供商 | 輸入價格 | 輸出價格 |
|---|---|---|
| Anthropic | 1.0M | 5.0M |