Amazon Nova Pro is a cutting-edge multimodal model designed to handle text, image, and video inputs with advanced processing capabilities. Featuring a 300K-token context window, it excels in document analysis, visual question answering, and complex agent-driven workflows. As part of the Amazon Nova foundation models, it supports fine-tuning and distillation, enabling deep customization for various applications.
| Gemini 3 Pro | Nova Pro | |
|---|---|---|
Web Site
| ||
Provider
| ||
Chat
| ||
Release Date
| ||
Modalities
| text images voice video | text images video |
API Providers
| Google AI Studio, Vertex AI, Gemini app | Amazon Bedrock |
Knowledge Cut-off Date
| 2025-01 | Purposefully not disclosed |
Open Source
| No | No |
Pricing Input
| $2 per million tokens | $0.80 per million tokens |
Pricing Output
| $12 per million tokens | $3.20 per million tokens |
MMLU
| - | 85.9% CoT Source |
MMLU-Pro
| - | Not available |
MMMU
| 81% Pro Source | Not available |
HellaSwag
| - | Not available |
HumanEval
| - | 89% pass@1 Source |
MATH
| - | 76.6% CoT Source |
GPQA
| 91.9% Diamond, Scientific knowledge, No tools Source | 46.9% Main Source |
IFEval
| - | 92.1% Source |
SimpleQA
| 72.1% Parametric knowledge Source | - |
AIME 2024 | - | - |
AIME 2025 | 95% Source | - |
Aider Polyglot
| - | - |
LiveCodeBench v5
| - | - |
Global MMLU (Lite)
| - | - |
MathVista
| - | - |
Mobile Application | - |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2026 All Right Reserved.