Claude Sonnet 4.6 (Non-reasoning, High)
AnthropicClaudeProprietary
描述
Claude Sonnet 4.6 is a full upgrade of the model's skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Users preferred Sonnet 4.6 over Sonnet 4.5 approximately 70% of the time. First Sonnet-class model with 1M token context window (beta) and context compaction. Major improvement in computer use skills compared to prior Sonnet models. Default model on Free and Pro plans. Pricing: $3/$15 per million tokens (input/output).
发布日期
2026-02-17
参数规模
—
上下文长度
1.0M
支持模态
audio, image, pdf, text, video
能力雷达图
60
general
60
coding
70
reasoning
77
science估算
80
agents
80
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
Finance Agent
63.3%自报
Finance Agent v2
51.0%
Code
DeepSWE 1.1
30.0%
Communication
Tau2 Telecom
97.9%自报
Tau2 Retail
91.7%自报
Language
MMMLU
89.3%自报
Legal
Legal Agent Benchmark
5.4%
Math
LiveBench
75.5%
Multimodal
OSWorld
72.5%自报
Reasoning
GPQANYU + Cohere + Anthropic (2023)
89.9%自报
SWE-Bench Verified
79.6%自报
BrowseCompOpenAI (2025)
74.7%自报
MCP Atlas
61.3%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
59.1%自报
ARC-AGI v2
58.3%自报
Humanity's Last Exam
49.0%自报
Vision
MMMU-Pro
75.6%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Language90
Physics90
Biology90
Chemistry90
Communication90
Frontend Development80
Tool Calling80
Math70
Multimodal70
Search70
Reasoning60
Spatial Reasoning60
Finance60
General60
Code60
Vision60
Agents50
Long Context40
Healthcare20
Legal10
定价
输入价格$3 / 1M tokens
输出价格$15 / 1M tokens
混合价格(3:1)$6 / 1M tokens
缓存读取价格$0.3 / 1M tokens
缓存写入价格$3.75 / 1M tokens
速度
Tokens/秒42.4
首Token延迟1.22s
首回答延迟1.22s
供应商价格排行
供应商价格排行
2 个供应商
最便宜: Anthropic最贵: DeepInfra
供应商输入输出
1Anthropic主要
$3
$15
2DeepInfra
$3
$15
比较该模型在不同 API 供应商之间的定价。