Skip to main content
AITier

Nova Micro

AmazonAmazonProprietary

Description

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.

Release Date
2024-12-03
Parameters
—
Context Length
128K
Modalities
text

Capability Radar

22
general
8
coding
19
reasoning
20
scienceest.
60
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Code Ranking426
9.0
AA
General Ranking414
23.0
AA
Math Reasoning305
19.0
AA
Science424
18.0
AA

Benchmark Scores (LLM Stats)

Biology

GPQA40.0%SR

Code

HumanEval81.1%SR

Economics

FinQA65.2%SR
CRAG43.1%SR

Finance

MMLU77.6%SR

General

ARC-C90.2%SR
IFEval87.2%SR
BFCL56.2%SR

Language

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

Math

GSM8k92.3%SR
DROP79.3%SR
MATH69.3%SR

AA Evaluation Indices

Intelligence Index
10.3
Math Index
6.0
Coding Index
4.1
Math 500
0.7
Mmlu Pro
0.5
Gpqa
0.4
Ifbench
0.3
Livecodebench
0.1
Tau2
0.1
Lcr
0.1
Scicode
0.1
Aime
0.1
Aime 25
0.1
Hle
0.0
Terminalbench Hard
0.0

LLM Stats Category Scores

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

Pricing

Input Price$0.035 / 1M tokens
Output Price$0.14 / 1M tokens
Blended Price (3:1)$0.061 / 1M tokens

Speed

Tokens/sec325.7 tokens/s
Time to First Token0.65s
Time to Answer0.65s

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats