Claude Opus 4
AnthropicClaudeProprietary
描述
Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family. It delivers sustained performance on complex, long-running tasks and agent workflows. Opus 4 excels at coding, advanced reasoning, and can use tools (like web search) during extended thinking. It supports parallel tool execution and has improved memory capabilities.
發布日期
2025-05-22
參數規模
—
上下文長度
200K
支援模態
file, image, text
能力雷達圖
80
general
60
coding
80
reasoning
68
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
39.2%自報
Biology
GPQA
79.6%自報
Code
SWE-Bench Verified
72.5%自報
Communication
TAU-bench Retail
81.4%自報
TAU-bench Airline
59.6%自報
General
MMMLU
88.8%自報
MMMU (validation)
76.5%自報
Math
AIME 2025
75.5%自報
Reasoning
ARC-AGI v2
8.6%自報
AA 評測指數
暫無 AA 評測資料
LLM Stats 分類評分
Language90
Biology80
Chemistry80
General80
Healthcare80
Math80
Multimodal80
Physics80
Tool Calling70
Communication70
Frontend Development70
Code60
Reasoning60
Vision40
Agents40
Spatial Reasoning10
定價
輸入價格$15 / 1M tokens
輸出價格$75 / 1M tokens
混合價格(3:1)$30 / 1M tokens
速度
暫無速度資料
可用提供商
(LS 內部計價單位)暫無提供商資料