ChatGPT leads AI image generation in blind tests, Gemini best value, Grok fastest
Blind human-preference tests rank OpenAI's ChatGPT, powered by GPT Image 2, as the top AI image generator as of late 2026. GPT Image 2 scored 1,339 Elo on the Artificial Analysis Text-to-Image Arena and 506 on LLM Stats' October rankings from over 11,000 votes, well ahead of xAI's Grok Imagine Image 2.0 at 362. ChatGPT excels at prompt accuracy, conversational editing, and readable text in…
Key points
- ChatGPT's GPT Image 2 leads blind-vote leaderboards with 1,339 Elo and 506 LLM Stats score
- Gemini's free tier allows roughly twice as many images as ChatGPT; paid plans from $4.99/month
- Grok Imagine Image 2.0 ranks second on LLM Stats, offers image-to-video and a "Spicy" mode
Google's Gemini, using its Nano Banana model family, ranks fifth on Artificial Analysis at 1,254 Elo but is cited as the best value. Its free tier allows roughly twice as many images as ChatGPT's, and paid plans start at $4.99 per month for Google AI Plus. Reviewers highlight Gemini's strength in photo editing, character consistency, and text rendering.
xAI's Grok Imagine Image 2.0 places second on LLM Stats and is noted for cinematic style, speed, and a built-in image-to-video feature. It also offers a "Spicy" mode allowing suggestive content, though free access is minimal after xAI restricted it to paid users following deepfake misuse. Anthropic's Claude does not generate photos or illustrations; it creates diagrams, charts, SVG code, and design layouts via Claude Design, with CEO Dario Amodei calling the omission a deliberate choice over fake-content concerns.
The story so far
2 episodes →- ChatGPT leads AI image generation in blind tests, Gemini best value, Grok fastestthis story
ChatGPT vs Gemini vs Grok vs Claude: Which AI Makes the Best Images in 2026? Blind Tests Crown a Clear Winner
ibtimes.com.au · 1 November 2026
Loading the full article…
This text was published by ibtimes.com.au and written by George Anton. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Nace AI releases Drex Max v1, a 27B decision model that runs locally on Apple Silicon · 1 src
- AI News Summary 11/1 | Claude's Ultra 5-hour limit removed, 9 AI infrastructure companies breached, and more · 1 src
- Claude removes Opus 4.8 fast mode, users should migrate to Opus 5.5 · 1 src
- Anthropic renames $200 Claude plan to Ultra and removes 5-hour limit · 1 src
- Krlntn builds neural network that boots PC from 512‑byte MBR · 1 src
Comments
via GitHub Discussions