Same-prompt PvZ clone test shows GPT-6 Sol clearly beating GPT-5.6 Sol
___Patrice___ · x · 2026-09-25
Responding to claims that "GPT-6 Sol sucks compared to GPT-5.6 Sol, it's GPT-5.6 Terra recycled," user Patrice gave both models the same prompt: build a full-blown Plants vs. Zombies clone.
Side-by-side results of 6 Sol vs. 5.6 Sol show a clear improvement, with the poster adding "no comment." A hands-on rebuttal to the regression controversy around the new model.
More from Models
- Micius-Flash: 27B Multimodal Model for Hardware and Semiconductor Agents — zhiman-ai · 2026-11-11
- Baidu says RSI auto-optimized ERNIE inference, 6.24x decode speedup on Kunxin P800 — xiaohu · 2026-11-11
- Baidu's ECHO: multi-token prediction reusing the last layer as a drafter — xiaohu · 2026-11-11
- ERNIE 5.5 Flash Preview: 280B-param multi-router MoE activating only 14B per token — xiaohu · 2026-11-11
- ERNIE 5.5 recreates the Pelican test: 117-second animation drawn frame-by-frame in Python — xiaohu · 2026-11-11
- 35,000+ Grok-built apps exposed patient data, plaintext passwords, and sales pipeline — The Decoder · 2026-11-11