Gemini 3.7 vs Qwen 3.8 Max vs Kimi K3
I gave all three models the exact same one-line prompt. Results: • Kimi K3 → ~8 min • 890 lines of code • Qwen 3.8 Max → ~12 min • 1,190 lines of code • Gemini 3.7 → ~2 min • 858 lines of code My take: • Kimi K3 → Excellent
Qwen 3.8 27B just created this arena survivor Three.js game in ONE SHOT using my AI game asset library.
And the best part? it costed me $0. I hosted it locally on my RTX 3060, so there were no API bills, censorship, or rate limits. The output is genuinely Fable-level. It
Me running Qwen 3.8-27B on my machine 🚀
Patiently waiting for Qwen 3.8 like it’s Christmas morning
You have reached the end of the archive
All of qwen38