Compare AI models

Specifications
Parameters
236B1.5B/7B/72B
Context window
128k4k
These models have no shared benchmark scores.
Overview
CompanyDeepSeekQwen
Release dateDec 10 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2.5 (Revised) 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 82 days before DeepSeek V2.5 (Revised), so benchmark comparisons should account for the intervening progress.

DeepSeek V2.5 (Revised) has 236B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 128k (DeepSeek V2.5 (Revised)) vs 4k (Qwen2.5-Math).

Direct benchmark comparisons are unavailable — DeepSeek V2.5 (Revised) and Qwen2.5-Math don't publish scores on any of the same benchmarks.