Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
AnthropicClaude
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
58
general
74
coding
94
reasoning
72
science估算
30
agents
70
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)
Agents
GDPval-AA
1861.00 / 3000自报
BrowseComp
90.8%自报
OSWorld 2.0
70.6%自报
DeepSWE 1.1
68.8%自报
FrontierCode 1.1
53.4%自报
FrontierCode
53.4%自报
Frontier-Bench v0.1
43.3%自报
AutomationBench
26.0%自报
Legal Agent Benchmark
11.7%自报
Biology
BioMysteryBench
90.1%自报
General
ARC-AGI-3
30.2%自报
Healthcare
HealthBench Professional
59.8%自报
Math
Humanity's Last Exam
64.7%自报
AA 评测指数
Coding Index77.0
Intelligence Index60.1
Gpqa0.9
Terminalbench V2 10.9
Lcr0.7
Scicode0.6
Hle0.5
Tau Banking0.3
LLM Stats 分类评分
Finance100
Legal100
Agents100
Reasoning100
General100
Search90
Multimodal70
Vision70
Math60
Healthcare60
Code60
Tool Calling30
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60.4
首Token延迟22.56s
首回答延迟22.56s
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主要
$5
$25
比较该模型在不同 API 供应商之间的定价。