Compare AI models

Specifications
Parameters
671B—
Context window
128k1M
Benchmarks
LiveCodeBench
65.9%37.8%
MMLU-Pro
84%64.5%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Qwen2.5-Turbo (1M) on 2 of the 2 benchmarks they both report (LiveCodeBench, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 66 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 1M (Qwen2.5-Turbo (1M)). DeepSeek R1 is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, DeepSeek R1 leads at 65.9% vs Qwen2.5-Turbo (1M) at 37.8%. On MMLU-Pro, DeepSeek R1 leads at 84% vs Qwen2.5-Turbo (1M) at 64.5%.