Compare AI models

Specifications
Parameters
236B4B/30B/235B
Context window
128k256k
These models have no shared benchmark scores.
Overview
CompanyDeepSeekQwen
Release dateJun 28 2024Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2-0628 and Qwen3-2507 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2-0628 shipped 388 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

DeepSeek V2-0628 has 236B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (DeepSeek V2-0628) vs 256k (Qwen3-2507).

Direct benchmark comparisons are unavailable — DeepSeek V2-0628 and Qwen3-2507 don't publish scores on any of the same benchmarks.