Claude 3 Sonnet
AnthropicClaudeProprietary
描述
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
發布日期
2024-03-04
參數規模
—
上下文長度
—
支援模態
image, text
能力雷達圖
24
general
19
coding
23
reasoning
27
science估算
0
agents
80
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Biology
GPQA
40.4%自報
Code
HumanEval
73.0%自報
Finance
MMLU
79.0%自報
MMLU-Pro
56.8%自報
General
ARC-C
93.2%自報
Language
BIG-Bench Hard
82.9%自報
Math
GSM8k
92.3%自報
MGSM
83.5%自報
DROP
78.9%自報
MATH
43.1%自報
Reasoning
HellaSwag
89.0%自報
AA 評測指數
Intelligence Index10.3
Mmlu Pro0.6
Math 5000.4
Gpqa0.4
Scicode0.2
Livecodebench0.2
Aime0.0
Hle0.0
LLM Stats 分類評分
Code70
Finance70
General70
Healthcare70
Language70
Legal70
Math70
Reasoning70
Biology40
Chemistry40
Physics40
定價
輸入價格$3 / 1M tokens
輸出價格$15 / 1M tokens
混合價格(3:1)$6 / 1M tokens
速度
Tokens/秒0.0 tokens/s
首Token延遲0.00s
首回答延遲0.00s
可用提供商
(LS 內部計價單位)暫無提供商資料