Claude 3.7 Sonnet (Non-reasoning)
AnthropicClaudeProprietary
描述
The most intelligent Claude model and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can produce near-instant responses or extended, step-by-step thinking that is made visible to the user. Shows particularly strong improvements in coding and front-end web development.
發布日期
2025-02-24
參數規模
—
上下文長度
200K
支援模態
file, image, text
能力雷達圖
42
general
32
coding
35
reasoning
44
science估算
70
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
Terminal-Bench
35.2%自報
Biology
GPQA
84.8%自報
Code
SWE-Bench Verified
70.3%自報
Communication
TAU-bench Retail
81.2%自報
TAU-bench Airline
58.4%自報
General
IFEval
93.2%自報
MMMLU
86.1%自報
MMMU
75.0%自報
Math
MATH-500
96.2%自報
AIME 2024
80.0%自報
AIME 2025
54.8%自報
AA 評測指數
Intelligence Index30.8
Coding Index26.7
Math Index21.0
Math 5000.8
Mmlu Pro0.8
Gpqa0.7
Tau20.5
Lcr0.5
Ifbench0.4
Livecodebench0.4
Scicode0.4
Aime0.2
Terminalbench Hard0.2
Aime 250.2
Hle0.0
LLM Stats 分類評分
Structured Output90
Instruction Following90
Language90
Vision80
Biology80
Chemistry80
General80
Healthcare80
Math80
Multimodal80
Physics80
Tool Calling70
Communication70
Frontend Development70
Reasoning70
Code50
Agents40
定價
輸入價格$3.75 / 1M tokens
輸出價格$15 / 1M tokens
混合價格(3:1)$6.563 / 1M tokens
速度
Tokens/秒0.0 tokens/s
首Token延遲0.00s
首回答延遲0.00s
可用提供商
(LS 內部計價單位)暫無提供商資料