DeepSeek V4 Flash Builds Flappy Bird for $0.0005 in Coding Test
BLUECOW009 · x · 2026-08-01
A recent head-to-head test of AI coding models has drawn significant attention. Using a single prompt, DeepSeek V4 Flash, Kimi K3, and GLM 5.2 were tasked with generating a Flappy Bird game, evaluated on gameplay, UI/UX, and cost:
- Kimi K3: Scored 9.5/10 with a generation cost of $0.0740, offering the best experience.
- GLM 5.2: Scored 9/10 at $0.0480 per generation, showing high polish.
- DeepSeek V4 Flash: Scored 7/10 at a mere $0.0005 per generation. While about 150x cheaper than the others, the resulting game was noticeably rougher around the edges.
More from coding & agent
- Agent named 'Ilya' reportedly scores 1.1pt higher on benchmarks — daniel_mac8 · 2026-10-16
- Gemini CLI fix: substring matching inlined unrequested binary files into model context — priyanshu1976 · 2026-10-16
- Building AI agents on real healthcare claims data: the domain work that makes them work — alex_verem · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Vibe-coded iPhone Duo sniping bot built with Codex in 17 minutes, 41 tests passing — xiaohu · 2026-10-16
- Long-term multiplayer agent memory tool tops BEAM memory benchmark — CurieuxExplorer · 2026-10-16