Bullshit Benchmark
Shares rank 5 of 10 AI benchmarks by recommenders
Praised as a clever benchmark that surfaces behavior differences between AI labs' models and reflects real-world utility.
Praised as a clever benchmark that surfaces behavior differences between AI labs' models and reflects real-world utility.
9 people gave an opinion
- recommend it
- 9
- criticize it
- 0
- approval share
- 100%
Recommended in 6 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: not recommended
- September 2026: 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.
- Nobody criticizes itNeeds 2 to 1 or better, met.
- Recommended in 6 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
Clever, well-designed benchmark approach
“the bullshit benchmark seems like a clever approach to testing at least some of that”
Comment from 6 Mar 2026 in “GPT-5.4 Thinking System Card” “my favorite LLM benchmark of all time”
Comment from 22 Sep 2026 in “Ask HN: How do you interview devs in a post-AI world?” “That's a nice benchmark + website”
Comment from 4 Mar 2026 in “GPT‑5.3 Instant” Reflects real-world model utility
“bullshit bench and simple bench are the only benchmarks that reflect real world utility”
Comment from 23 Jul 2026 in “OpenAI's accidental cyberattack against Hugging Face is science fiction” “Such a great project that could automate a lot vibes testing hopefully!”
Comment from 25 Feb 2026 in “Bullshit Benchmark Explorer”
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 |
| Bullshit BenchmarkThis page | 9 | 0 | 100% | 6 | — | — |
What people said
8 of the 9 comments that mention it, newest first. Each links to the original comment.
“my favorite LLM benchmark of all time”
“That is an interesting benchmark! Though I wonder if it is probing at certain behaviors”
“bullshit bench and simple bench are the only benchmarks that reflect real world utility”
“I think it surfaces important differences between the behavior of the models from different labs.”
“For a less biased source, check out BSBench”
“the bullshit benchmark seems like a clever approach to testing at least some of that”
“That's a nice benchmark + website”
“Such a great project that could automate a lot vibes testing hopefully!”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.