Nova Micro
AmazonAmazonProprietary
描述
A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks. Optimized for speed and efficiency while preserving high accuracy on key benchmarks.
發布日期
2024-12-03
參數規模
—
上下文長度
128K
支援模態
text
能力雷達圖
22
general
8
coding
19
reasoning
20
science估算
60
agents
0
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
40.0%自報
Code
HumanEval
81.1%自報
Economics
FinQA
65.2%自報
CRAG
43.1%自報
Finance
MMLU
77.6%自報
General
ARC-C
90.2%自報
IFEval
87.2%自報
BFCL
56.2%自報
Language
Translation Set1→en COMET22
88.7%自報
Translation en→Set1 COMET22
88.5%自報
BBH
79.5%自報
Translation Set1→en spBleu
42.6%自報
Translation en→Set1 spBleu
40.2%自報
SQuALITY
18.8%自報
Math
GSM8k
92.3%自報
DROP
79.3%自報
MATH
69.3%自報
AA 評測指數
Intelligence Index10.3
Math Index6.0
Coding Index4.1
Math 5000.7
Mmlu Pro0.5
Gpqa0.4
Ifbench0.3
Livecodebench0.1
Tau20.1
Lcr0.1
Scicode0.1
Aime0.1
Aime 250.1
Hle0.0
Terminalbench Hard0.0
LLM Stats 分類評分
Structured Output90
Instruction Following90
Code80
Healthcare80
Legal80
Math80
General70
Reasoning70
Tool Calling60
Finance60
Language60
Economics50
Biology40
Chemistry40
Physics40
Search40
Summarization20
Long Context20
定價
輸入價格$0.035 / 1M tokens
輸出價格$0.14 / 1M tokens
混合價格(3:1)$0.061 / 1M tokens
速度
Tokens/秒325.7 tokens/s
首Token延遲0.65s
首回答延遲0.65s
可用提供商
(LS 內部計價單位)暫無提供商資料