• benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.

Independent, task-by-task testing across coding, control, and design workloads shows where DeepSeek V4.1 Flash actually performs versus its benchmark claims, useful signal for anyone deciding whether to route real work to this open model.

• 00:00Intro
• 00:55First Look
• 02:26Technical Look
• 05:09Testing Setup
• 05:48Browser OS Test
• 10:22C++ Skate Game Test
• 14:00Robot Arm Control Test
• 17:11Subway FPS Test
• 20:14Blender & Godot Wrestling Game Test
• 26:57C++ Rally Game Test
• 30:533D CAD Model Test
• 32:45Watch Website Test
• 36:29Testing Cost & Overview
• 37:34Results Overview

• videoGPT-6 Astra vs Claude Fable 5.1 – The REAL Comparison Test!
• videoMeta Muse Spark 1.3 Is HERE – Is THIS a Real Opus Competitor?
• videoClaude Fable 5.1 Is INSANE – Hands-On With the BEST Model Yet!
• videoTencent HY4 Is HERE – Is THIS Tencent’s Next Frontier Model?

• videoDeepSeek V4 Pro Is HERE – Is THIS the BEST Open Model Yet?Bijan Bowen
• videoDeepSeek V4 FlashBijan Bowen
• videoDeepSeek V4 Flash Vision Is INSANE – Tested With DeepSeek Harness!Bijan Bowen

Checking sign-in…

Loading comments…