Gemini 2.0 Flash is Google's high-performance, low-latency model designed to drive advanced agentic experiences. Equipped with native tool integration, it supports multimodal inputs, including text, images, video, and audio. Offering substantial improvements over previous versions, the model balances efficiency, speed, and enhanced capabilities for seamless real-time interactions.
Amazon Nova Lite is a versatile multimodal model designed to process text, image, and video inputs, producing text-based outputs. Featuring a 300K-token context window, it is well-suited for real-time interactions, document analysis, and visual question answering. As part of the Amazon Nova foundation models, it supports fine-tuning and distillation, enabling advanced customization.
| Gemini 2.0 Flash | Nova Lite | |
|---|---|---|
Provider | ||
Web Site | - | |
Release Date | Dec 11, 2024 4 months ago | Dec 02, 2024 4 months ago |
Modalities | text images voice video | text images video |
API Providers | Google AI Studio, Vertex AI | Amazon Bedrock |
Knowledge Cut-off Date | 08.2024 | Purposefully not disclosed |
Open Source | No | No |
Pricing Input | $0.10 per million tokens | $0.06 per million tokens |
Pricing Output | $0.40 per million tokens | $0.24 per million tokens |
MMLU | Not available | 80.5% CoT Source |
MMLU Pro | 77.6% Source | Not available |
MMMU | 71.7% Source | Not available |
HellaSwag | Not available | Not available |
HumanEval | Not available | 85.4% pass@1 Source |
MATH | 90.9% Source | 73.3% CoT Source |
GPQA | 60.1% Diamond Source | 42% Main Source |
IFEval | Not available | 89.7% Source |
Mobile Application | - |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2025 All Right Reserved.