Compare AI models

Specifications
Parameters
671B1.5B/7B/72B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyDeepSeekQwen
Release dateJan 20 2025Aug 8 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 and Qwen2-Math don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2-Math shipped 165 days before DeepSeek R1, so benchmark comparisons should account for the intervening progress.

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

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