Claude 3.5 Sonnet
AnthropicClaudeProprietary
描述
Claude 3.5 Sonnet is a powerful AI model with industry-leading software engineering skills. It excels in coding, planning, and problem-solving, with significant improvements in agentic coding and tool use tasks. The model includes computer use capabilities in public beta, allowing it to interact with computer interfaces like a human user.
发布日期
2024-10-22
参数规模
—
上下文长度
—
支持模态
image, text
能力雷达图
80
general
70
coding
90
reasoning
60
science估算
60
agents
100
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
| 领域 | #排名 | 分数 | 来源 |
|---|---|---|---|
| 多模态榜 | 6 | 65.0 | LS |
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
OSWorld Extended
22.0%自报
OSWorld Screenshot-only
14.9%自报
Biology
GPQANYU + Cohere + Anthropic (2023)
67.2%自报
Code
HumanEvalOpenAI (2021)
93.7%自报
SWE-Bench Verified
49.0%自报
Communication
TAU-bench Retail
69.2%自报
TAU-bench Airline
46.0%自报
Finance
MMLU
90.4%自报
MMLU-Pro
77.6%自报
General
MMMU
68.3%自报
Image To Text
DocVQADocVQA (2020)
95.2%自报
Language
BIG-Bench Hard
93.1%自报
Math
GSM8k
96.4%自报
MGSM
91.6%自报
DROP
87.1%自报
MATH
78.3%自报
MathVista
67.7%自报
Multimodal
AI2D
94.7%自报
ChartQAMasry et al. (2022)
90.8%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))Image To Text100
Math90
Language90
Legal80
Multimodal80
Reasoning80
Finance80
General80
Healthcare80
Vision80
Physics70
Biology70
Chemistry70
Code70
Communication60
Tool Calling60
Frontend Development50
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据