← Blog
RESEARCH

Qwen 3.8 27B vs DeepSeek V4 Pro 0813 vs Gemini 3.7 Flash on FlappyBench

Tested FlappyBench on Qwen 3.8 27B, DeepSeek V4 Pro 0813, and Gemini 3.7 Flash with /design command.

Team Command Code
1 min read
Aug 21, 2026

Tested FlappyBench on Qwen 3.8 27B, DeepSeek V4 Pro 0813, and Gemini 3.7 Flash with /design command. All scored 9/10, it comes down to cost, quality, and iterations.

  • DeepSeek V4 Pro ($0.0036): Low cost, solid, but movement and spacing need work.
  • Qwen 3.8 27B ($0.0068): One-shot, playable, with minor UI finish.
  • Gemini 3.7 Flash ($0.0083): Needed 2–3 iterations to catch up.

Qwen for the best one-shot. DSV4 for the best value.

Our engineering and design team has been testing 26+ side-by-side comparisons across frontier and open models. All runs are public and open source. Benchmark for this demo here: github.com/CommandCodeAI/slash-design-showcase/tree/main/flappy-bird

Try Command Code

The best coding agent for open models, in your terminal or on your desktop.

1npm i -g command-code

Desktop App · Docs · X · Discord

Share this article