AI Dynamics

Global AI News Aggregator

About

Real Repository Bug Tests Compare Frontier Coding Models

So I tested DeepSeek V4.1 Flash 1017 on real work. 2 repos. 105 hidden bugs. Find and fix what you can. The first results: Muse Wonder Full 1.0 (max): 42
Opus 5.5 (max): 41.7
Gemini 4 Argon (high): 40.7
DeepSeek V4.1 Flash 1017 (max): 34 🟣
Grok 4.7 (xhigh): 29
Qwen3.8-Max

→ View original post on X — @deeplearn007