GenAI Showdown
Shares rank 5 of 10 AI benchmarks by recommenders
People recommend it as a go-to comparison of image generation models, including locally runnable ones. Critics question whether the rankings are fair, saying they seem AI-judged and ignore style.
People recommend it as a go-to comparison of image generation models, including locally runnable ones. Critics question whether the rankings are fair, saying they seem AI-judged and ignore style.
12 people gave an opinion
- recommend it
- 9
- criticize it
- 3
- approval share
- 75%
Recommended in 5 of 13 months
- November 2025: recommended
- December 2025: recommended
- January 2026: recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 9 people recommend itNeeds 10 or more, not met.
- 3 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 5 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Best benchmark for image models
“probably the best one out there for image models”
Comment from 16 Dec 2025 in “GPT Image 1.5” “Love this benchmark, always the first place I look.”
Comment from 17 Dec 2025 in “GPT Image 1.5”
What people warn about
Each mark is one comment
Rankings seem AI-judged and absurd
“The photo rankings on this page are so absurd that the only reasonable explanation is that they were judged by an AI.”
Comment from 5 Aug 2026 in “Qwen 3.0 Image Pro” Overstates confidence in structured data
“Your testing suite is the perfect example that structured data implies false confidence.”
Comment from 17 Jan 2026 in “FLUX.2 [Klein]: Towards Interactive Visual Intelligence” Does not check style
“this benchmark is not checking style at all”
Comment from 26 Nov 2025 in “FLUX.2: Frontier Visual Intelligence” Before and After buttons swapped
“Cool site, thanks! By the way, the "Before" and "After" buttons are swapped.”
Comment from 21 Nov 2025 in “Nano Banana Pro”
Other AI benchmarks people recommend
The four most recommended other AI benchmarks, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Artificial Analysis | 62 | 46 | 57% | 11 | — | — |
| LMArena | 39 | 40 | 49% | 11 | — | — |
| ARC-AGI | 22 | 24 | 48% | 8 | — | — |
| OCR Arena | 11 | 4 | 73% | 4 | — | Approved |
| GenAI ShowdownThis page | 9 | 3 | 75% | 5 | — | — |
What people said
8 of the 12 comments that mention it, newest first. Each links to the original comment.
“The photo rankings on this page are so absurd that the only reasonable explanation is that they were judged by an AI.”
“You can click "View All Models" and filter the list down to just locally runnable options”
“Very cool site - I think I saw it before here on HN, and I liked it a lot.”
“Your testing suite is the perfect example that structured data implies false confidence.”
“Love this benchmark, always the first place I look.”
“probably the best one out there for image models”
“this benchmark is not checking style at all”
“Cool site, thanks! By the way, the "Before" and "After" buttons are swapped.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.