跳转到主要内容
AITier

Claude Sonnet 4.6 (Non-reasoning, High Effort)

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

32
general
47
coding
80
reasoning
55
science
80
agents
80
multimodal

排行榜排名

领域#排名分数来源
智能体能力模型榜39
53.0
LS
代码能力榜100
73.0
AA
通用能力榜176
59.0
AA
科学能力161
61.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Agents

BrowseCompOpenAI (2025)74.7%自报
OSWorld72.5%自报
Finance Agent63.3%自报
MCP Atlas61.3%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)59.1%自报
Finance Agent v251.0%
DeepSWE 1.130.0%
Legal Agent Benchmark5.4%

Biology

GPQANYU + Cohere + Anthropic (2023)89.9%自报

Code

SWE-Bench Verified79.6%自报

Communication

Tau2 Telecom97.9%自报
Tau2 Retail91.7%自报

General

MMMLU89.3%自报
MMMU-Pro75.6%自报
LiveBench75.5%

Math

Humanity's Last Exam49.0%自报

Reasoning

ARC-AGI v258.3%自报

AA 评测指数

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
36.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Lcr(Artificial Analysis)
0.6
Scicode(UIUC + Argonne National Lab (2024))
0.5
Terminalbench Hard(Stanford × Laude Institute (2026))
0.5
Ifbench(Google Research (2023))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats 分类评分

(LLM Stats (zeroeval))
Physics
90
Language
90
Biology
90
Chemistry
90
Communication
90
Frontend Development
80
Tool Calling
80
Math
70
Multimodal
70
Search
70
Reasoning
60
Spatial Reasoning
60
Finance
60
General
60
Code
60
Vision
60
Agents
50
Long Context
40
Healthcare
20
Legal
10

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0.0
首Token延迟0.00s
首回答延迟0.00s

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
$0.00002

比较该模型在不同 API 供应商之间的定价。

外部链接

LLM StatsArtificial Analysis