Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B—
Context window
—32k
Benchmarks
LiveCodeBench
57.5%38.7%
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Jan 28 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 Distill leads Qwen2.5-Max on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek R1 Distill shipped 8 days before Qwen2.5-Max, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill is open weight, while Qwen2.5-Max is closed.

On LiveCodeBench, DeepSeek R1 Distill leads at 57.5% vs Qwen2.5-Max at 38.7%.