---
title: "Nova Micro Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Nova Micro."
source: "https://rankedagi.com/models/nova-micro"
---

# Nova Micro

| Field | Value |
| --- | --- |
| Organization | Amazon |
| License | Proprietary |
| Version | Latest |
| Released | 2024-12-03 |
| Context window | 128K |
| Input cost per million tokens | $0.04 |
| Output cost per million tokens | $0.14 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 34.2% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 40.2% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1181 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 20.2% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 38.4% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 40.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1198 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 81.1% | HumanEval coding benchmark |  |
| MMLU | knowledge | 76.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 1.6% | Computed using Vectara's Hallucination Evaluation Model, also known as HHEM. This evaluates how often an LLM introduces hallucinations when summarizing a document. | https://github.com/vectara/hallucination-leaderboard |
| Artificial Analysis Quality Index | general | 66 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 41.2% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 41.6% | Overall RankedAGI score |  |