gpt.buzz
Sign in

Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

SelectedAlibaba logoQwen3 235B×DeepSeek logoDeepSeek-V4-Flash×DeepSeek logoDeepSeek-R1×Clear all
 
Alibaba logoQwen3 235B

Alibaba

DeepSeek logoDeepSeek-V4-Flash

DeepSeek

DeepSeek logoDeepSeek-R1

DeepSeek

VendorAlibabaDeepSeekDeepSeek
FamilyQwenDeepSeekDeepSeek
Release date2025-04-292026-04-222025-01-20
Context window128,000 tokens1,000,000 tokens128,000 tokens
Parameters235B284B (13B active)671B
Modalitytexttexttext
LicenseApache-2.0MITMIT
Sourceopen weightsopen weightsopen weights
DescriptionPredecessor to the Qwen3.6 family.Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.Reasoning-focused open-weight model.
Links

Add a model