跳转到主要内容

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.

发布日期
2024-12-03
参数规模
—
上下文长度
128K
支持模态
text

能力雷达图

20
general
14
coding
19
reasoning
26
science
60
agents
0
multimodal

排行榜排名

领域#排名分数来源
代码能力榜580
11.0
AA
通用能力榜572
21.0
AA
科学能力588
18.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)87.2%自报

Finance

FinQA65.2%自报

General

MMLU77.6%自报
BFCL56.2%自报

Language

Translation Set1→en COMET2288.7%自报
Translation en→Set1 COMET2288.5%自报
Translation Set1→en spBleu42.6%自报
Translation en→Set1 spBleu40.2%自报

Math

GSM8k92.3%自报
MATH69.3%自报

Reasoning

ARC-C90.2%自报
HumanEvalOpenAI (2021)81.1%自报
BBH79.5%自报
DROP79.3%自报
CRAG43.1%自报
GPQANYU + Cohere + Anthropic (2023)40.0%自报

Summarization

SQuALITY18.8%自报

AA 评测指数

(Artificial Analysis)
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
70.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
53.1
Gpqa(NYU + Cohere + Anthropic (2023))
35.8
Ifbench(Google Research (2023))
29.4
Tau2(Sierra + U Toronto + Vector Institute (2025))
14.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))
14.0
Lcr(Artificial Analysis)
13.0
Aime(MAA (Mathematical Association of America))
8.0
Math Index(Artificial Analysis)
6.0
Aime 25(MAA (Mathematical Association of America))
6.0
Intelligence Index(Artificial Analysis)
5.9
Hle(Center for AI Safety + Scale AI (2025))
4.6
Terminalbench Hard(Stanford × Laude Institute (2026))
1.5

LLM Stats 分类评分

(LLM Stats (zeroeval))
Chat
90
Instruction Following
90
Structured Output
90
Legal
80
Math
80
Healthcare
80
Code
80
Reasoning
70
General
70
Language
60
Finance
60
Tool Calling
60
Economics
50
Physics
40
Search
40
Biology
40
Chemistry
40
Long Context
20
Summarization
20

定价

输入价格$0.035 / 1M tokens
输出价格$0.14 / 1M tokens
混合价格(3:1)$0.061 / 1M tokens
缓存读取价格$0.00925 / 1M tokens
缓存写入价格$0.037 / 1M tokens

速度

Tokens/秒223.5
首Token延迟0.59s
首回答延迟0.59s

供应商价格排行

供应商价格排行

4 个供应商

最便宜: Amazon最贵: Amazon Bedrock
供应商输入输出
1Amazon主要
$0.035
$0.14
2OpenRouter
$0.035
$0.14
3Kilo Gateway
$0.035
$0.14
4Amazon Bedrock
$0.037
$0.148

比较该模型在不同 API 供应商之间的定价。

外部链接