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
19
general
13
coding
19
reasoning
20
scienceest.
60
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 446 | 10.0 | AA |
| General Ranking | 439 | 21.0 | AA |
| Math Reasoning | 305 | 19.0 | AA |
| Science | 447 | 18.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
40.0%SR
Code
HumanEval
81.1%SR
Economics
FinQA
65.2%SR
CRAG
43.1%SR
Finance
MMLU
77.6%SR
General
ARC-C
90.2%SR
IFEval
87.2%SR
BFCL
56.2%SR
Language
Translation Set1→en COMET22
88.7%SR
Translation en→Set1 COMET22
88.5%SR
BBH
79.5%SR
Translation Set1→en spBleu
42.6%SR
Translation en→Set1 spBleu
40.2%SR
SQuALITY
18.8%SR
Math
GSM8k
92.3%SR
DROP
79.3%SR
MATH
69.3%SR
AA Evaluation Indices
Math Index6.0
Intelligence Index4.7
Math 5000.7
Mmlu Pro0.5
Gpqa0.4
Ifbench0.3
Tau20.1
Livecodebench0.1
Lcr0.1
Scicode0.1
Aime0.1
Aime 250.1
Hle0.0
Terminalbench Hard0.0
LLM Stats Category Scores
Instruction Following90
Structured Output90
Legal80
Math80
Healthcare80
Code80
Reasoning70
General70
Language60
Finance60
Tool Calling60
Economics50
Physics40
Search40
Biology40
Chemistry40
Long Context20
Summarization20
Pricing
Input Price$0.035 / 1M tokens
Output Price$0.14 / 1M tokens
Blended Price (3:1)$0.061 / 1M tokens
Cache Read Price$0.00875 / 1M tokens
Speed
Tokens/sec251.0
Time to First Token0.67s
Time to Answer0.67s
Provider Price Ranking
Provider Price Ranking
6 providers
Cheapest: AmazonMost Expensive: NanoGPT
ProviderInputOutput
1AmazonPRIMARY
$0.035
$0.14
2OpenRouter
$0.035
$0.14
3Kilo Gateway
$0.035
$0.14
4Amazon Bedrock
$0.035
$0.14
5Vercel AI Gateway
$0.035
$0.14
6NanoGPT
$0.0357
$0.1394
Compare pricing across different API providers for this model.