Claude Opus 5 (Adaptive Reasoning, Max Effort)
AnthropicClaudeProprietary
描述
Claude Opus 5 is Anthropic's flagship general-access model, built for efficient agentic coding, knowledge work, scientific research, computer use, and problem-solving. Anthropic reports state-of-the-art results on Frontier-Bench v0.1 and GDPval-AA, substantial gains over Opus 4.8 across life-sciences evaluations, and support for configurable effort levels. It is available through the Claude API at the same $5/$25 per million input/output token price as Claude Opus 4.8.
发布日期
2026-07-24
参数规模
—
上下文长度
1.0M
支持模态
image, pdf, text
能力雷达图
54
general
75
coding
93
reasoning
73
science
40
agents
80
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
AutomationBench
26.0%自报
Biology
BioMysteryBench
90.1%自报
Code
DeepSWE 1.1
68.8%自报
Frontier-Bench v0.1
43.3%自报
Healthcare
HealthBench Professional
59.8%自报
Legal
Legal Agent Benchmark
11.7%自报
Multimodal
OSWorld 2.0
70.6%自报
Reasoning
BrowseCompOpenAI (2025)
90.8%自报
Humanity's Last Exam
64.7%自报
FrontierCode 1.1
53.4%
FrontierCode
53.4%自报
Terminal-Bench 4.0
51.8%
ARC-AGI-3
30.2%自报
AA 评测指数
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))93.2
Terminalbench V2 189.1
Lcr(Artificial Analysis)79.3
Coding Index(Artificial Analysis)78.0
Scicode(UIUC + Argonne National Lab (2024))56.4
Hle(Center for AI Safety + Scale AI (2025))54.9
Intelligence Index(Artificial Analysis)54.1
Tau Banking42.1
LLM Stats 分类评分
(LLM Stats (zeroeval))Science90
Search90
Biology90
Multimodal70
Vision70
Math60
General60
Healthcare60
Code60
Reasoning50
Agents50
Tool Calling40
Legal10
定价
输入价格$5 / 1M tokens
输出价格$25 / 1M tokens
混合价格(3:1)$10 / 1M tokens
缓存读取价格$0.5 / 1M tokens
缓存写入价格$6.25 / 1M tokens
速度
Tokens/秒51.6
首Token延迟38.16s
首回答延迟38.16s
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
$0.00001
$0.00003
比较该模型在不同 API 供应商之间的定价。