Third-Party Benchmark Claims DeepSeek V4.1 Flash Matches 98% of GPT-6 at 1.4% of Cost

ChrisUniverse · x · 2026-09-10

OpenDesignHQ benchmarked DeepSeek V4.1 Flash on everyday design tasks, claiming it hit 98% of GPT-6 Astra's score at 1.4% of the cost, with every other model scoring lower while costing more. A repost adds $0.023/task, 3x faster, 5% higher score. Unverified: neither model name has official confirmation, so treat with skepticism.

Related event: Independent Tests Show DeepSeek V4.1 Flash Delivers Near-Frontier Performance at ~1% the Cost(12 posts)→

Original post →

More from Models

Models channel →