GPT-Image-2.5 aces complex prompts but falls short of Midjourney's aesthetic sensibility
perilli · x · 2026-09-12
An industry reviewer tested OpenAI's new GPT-Image-2.5: its ability to follow complex prompt instructions is impressive, but its creative and aesthetic sensibility remains far behind Midjourney models—bigger improvements are needed to wow the media and entertainment industry. Even after extensive iteration with GPT-6 Astra Mac and ultimately GPT-6 Astra Ultra, the result still wasn't perfect.
More from Models
- Perplexity early evals: Gemini 4 Carbon tops WANDR benchmark for long-form research — AravSrinivas · 2026-10-31
- DeepSeek's silent downtime upgrade caught by the pelican bicycle test — teortaxesTex · 2026-10-31
- ARC Prize 2026 closes in 3 days as Yi-Chia Chen tops ARC-AGI-3 at 75.56% — GregKamradt · 2026-10-31
- Fable 5.5 Max stuns with gorgeous SVG of a pelican riding a bicycle, headed to Claude Code — ChrisGPT · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- NVIDIA Nemotron 3.5 scales LLM self-verification, +9-10 points on agentic benchmarks — sarahcat21 · 2026-10-31