跳轉到主要內容

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.

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

19
general
13
coding
19
reasoning
20
science
60
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜507
10.0
AA
通用能力榜501
21.0
AA
科學能力512
18.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)40.0%自報

Code

HumanEvalOpenAI (2021)81.1%自報

Economics

FinQA65.2%自報
CRAG43.1%自報

Finance

MMLU77.6%自報

General

ARC-C90.2%自報
IFEvalGoogle Research (2023)87.2%自報
BFCL56.2%自報

Language

Translation Set1→en COMET2288.7%自報
Translation en→Set1 COMET2288.5%自報
BBH79.5%自報
Translation Set1→en spBleu42.6%自報
Translation en→Set1 spBleu40.2%自報
SQuALITY18.8%自報

Math

GSM8k92.3%自報
DROP79.3%自報
MATH69.3%自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
6.0
Intelligence Index(Artificial Analysis)
4.4
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.5
Gpqa(NYU + Cohere + Anthropic (2023))
0.4
Ifbench(Google Research (2023))
0.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.1
Lcr(Artificial Analysis)
0.1
Scicode(UIUC + Argonne National Lab (2024))
0.1
Aime(MAA (Mathematical Association of America))
0.1
Aime 25(MAA (Mathematical Association of America))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Terminalbench Hard(Stanford × Laude Institute (2026))
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Structured Output
90
Instruction Following
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
快取讀取價格$0.00875 / 1M tokens

速度

Tokens/秒284.1
首Token延遲0.65s
首回答延遲0.65s

供應商價格排行

供應商價格排行

5 個供應商

最便宜: Amazon最貴: NanoGPT
供應商輸入輸出
1Amazon主要
$0.035
$0.14
2OpenRouter
$0.035
$0.14
3Kilo Gateway
$0.035
$0.14
4Amazon Bedrock
$0.035
$0.14
5NanoGPT
$0.0357
$0.1394

比較該模型在不同 API 供應商之間的定價。

外部連結