Compare AI models

Specifications
Parameters
671B1.5B/7B/72B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 and Qwen2.5-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Math shipped 123 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 128k (DeepSeek R1) vs 4k (Qwen2.5-Math).

Direct benchmark comparisons are unavailable — DeepSeek R1 and Qwen2.5-Math don't publish scores on any of the same benchmarks.