AIbase
EN
Home
AI Models Finder
Nova Micro
N

Nova Micro

A text-only model that can provide the lowest latency responses at a very low cost while maintaining strong performance on core language tasks. It is optimized for speed and efficiency while maintaining high accuracy in key benchmarks.
Intelligence(Relatively Weak)
Speed(Fast)
Input Supported Modalities
No
Is Reasoning Model
130,000
Context Window
128,000
Maximum Output Tokens
-
Knowledge Cutoff
Go Compare

Pricing

￥0.29 /M tokens
Input
￥1.01 /M tokens
Output
￥0.44 /M tokens
Blended Price

Quick Simple Comparison

Input

Output

Nova Premier
Nova Pro
￥0.8
Nova Lite
￥0.06

Basic Parameters

Nova MicroTechnical Parameters
Parameter Count
Not Announced
Context Length
130.00k tokens
Training Data Cutoff
Open Source Category
Proprietary
Multimodal Support
Text Only
Throughput
100
Release Date
2024-12-03
Response Speed
366.8,192 tokens/s

Benchmark Scores

Below is the performance of Nova Micro in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
28.29
Large Language Model Intelligence Level
Coding Index
11.67
Indicator of AI model performance on coding tasks
Math Index
39.17
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
53.1
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
35.8
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
4.7
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
14
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
9.4
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
79.9
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
70.3
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
8
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase