Gemini 4 Pro's viral PS5 SVG wows some, but critics say older models do far better
Angaisb_ · x · 2026-09-17
LuminaBench shared a PS5 SVG that Gemini 4 Pro generated in roughly 10 minutes, calling it possibly "one of the craziest outputs" they've gotten from an AI model and hyping the full release.
Replying, Angaisb pushed back: compared to what other current models can do—and even earlier Gemini models—the output quality is actually quite bad. A notable expectation gap around Gemini 4 Pro's real capabilities.
Related event: Alleged Gemini 4 Pro Output: Full PS5 SVG Stuns Community(2 posts)→
More from Models
- An AI forecaster has won the seasonal Metaculus Cup for the first time — NathanpmYoung · 2026-09-18
- After Jev's classification model hit, will generic regression and time-series foundation models be next as a service? — hichaelmart · 2026-09-18
- Jev vs generic model at same cost: 82.9% vs 58.8% on MMLU-Pro — simonguozirui · 2026-09-18
- DeepSeek V4.1-Flash vs V4-Pro Benchmarked: 3x Cheaper but Slower and Weaker Output — Arindam_1729 · 2026-09-18
- SemiAnalysis analyzed 616,300 OpenAI responses: GPT 5.6 Terra averages 1.94 tool calls per reply — AccBalanced · 2026-09-18
- Gemini's Japanese Apologies Are So Dramatic It Sounds Like Seppuku — DigitalFossilist · 2026-09-18