DeepSeek-R1 is a 671B parameter Mixture-of-Experts (MoE) model with 37B activated parameters per token, trained via large-scale reinforcement learning with a focus on reasoning capabilities. It incorporates two RL stages for discovering improved reasoning patterns and aligning with human preferences, along with two SFT stages for seeding reasoning and non-reasoning capabilities. The model achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks.
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.
| DeepSeek-R1 | Nova Lite | |
|---|---|---|
Provider | ||
Web Site | - | |
Release Date | Jan 21, 2025 3 months ago | Dec 02, 2024 4 months ago |
Modalities | text | text images video |
API Providers | DeepSeek, HuggingFace | Amazon Bedrock |
Knowledge Cut-off Date | Unknown | Purposefully not disclosed |
Open Source | Yes | No |
Pricing Input | $0.55 per million tokens | $0.06 per million tokens |
Pricing Output | $2.19 per million tokens | $0.24 per million tokens |
MMLU | 90.8% Pass@1 Source | 80.5% CoT Source |
MMLU Pro | 84% EM Source | Not available |
MMMU | - | Not available |
HellaSwag | - | Not available |
HumanEval | - | 85.4% pass@1 Source |
MATH | - | 73.3% CoT Source |
GPQA | 71.5% Pass@1 Source | 42% Main Source |
IFEval | 83.3% Prompt Strict Source | 89.7% Source |
Mobile Application | - |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2025 All Right Reserved.