DeepSeek V4.1 Flash outperforms GPT-6 Astra on design tasks at a fraction of the cost
- DeepSeek V4.1 Flash has been benchmarked against top AI models like GPT-6 Astra and achieved an impressive score of 81.2 out of 100, matching nearly 99% of GPT-6 Astra's performance on real-world design tasks.
Key points
- DeepSeek V4.1 Flash outperforms GPT-6 Astra on design tasks
- Costs about 7 times less for similar performance
- Only GPT-6 Astra scores higher in terms of output quality
Despite its superior performance, DeepSeek V4.1 Flash charges a mere $0.023 per finished design compared to GPT-6 Astra's $1.61, making it nearly 7 times cheaper for the same level of output quality.
Among 13 models tested, only GPT-6 Astra scored higher than DeepSeek V4.1 Flash on OpenDesign Arena's design benchmark. Other top performers like Claude Fable 5.1 and Qwen 3.8-Max cost more to run and perform worse in terms of output quality.
DeepSeek has a strategy for scaling its success by recruiting engineers in Beijing to build their own Code Harness, aiming to control the entire AI stack rather than just the model itself.
Model pages: GPT-6-Astra → · DeepSeek-V4.1-Flash → · Claude Fable 5.1 →
The story so far
3 episodes →- DeepSeek V4.1 Flash outperforms GPT-6 Astra on design tasks at a fraction of the costthis story
DeepSeek's New Model Nearly Matches GPT-6 Astra on Design—at 1.4% of the Cost
decrypt.co · 10 September 2026
Loading the full article…
This text was published by decrypt.co and written by Decrypt / Jose Antonio Lanz. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Meta releases Muse Spark Open, an 816B-parameter open-weight multimodal model with 42B active parameters and 1M-token context · 22 src
- Liquid AI releases d1-ultra decision model at $0.042 per million tokens · 1 src
- Google launches Gemini 4 Argon model globally for Pro and Ultra subscribers with introductory API pricing · 32 src
- Microsoft AI chief says in-house model beats OpenAI's using quarter of compute · 1 src
- NVIDIA releases Nemotron 3.5 Super VL and Bolt edge models for enterprise agents · 8 src
Comments
via GitHub Discussions