Compare AI models

Specifications
Parameters
8B—
Context window
—128k
Benchmarks
AIME 2024
86%36.7%
GPQA Diamond
61.1%69.5%
Overview
CompanyDeepSeekOpenAI
Release dateMay 29 2025Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1-0528 Qwen3 8B and GPT-4.5 are evenly matched across the 2 benchmarks they both report (AIME 2024, GPQA Diamond). GPT-4.5 shipped 91 days before DeepSeek R1-0528 Qwen3 8B, so benchmark comparisons should account for the intervening progress.

DeepSeek R1-0528 Qwen3 8B is open weight, while GPT-4.5 is closed.

On AIME 2024, DeepSeek R1-0528 Qwen3 8B leads at 86% vs GPT-4.5 at 36.7%. On GPQA Diamond, GPT-4.5 leads at 69.5% vs DeepSeek R1-0528 Qwen3 8B at 61.1%.