petergpt/bullshit-benchmark

bullshit-benchmark

✅ Recently maintained

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

1,904Stars
80Forks
+37-day stars

Python · MIT · Last push 2026-11-03

Official repository & installation ↗

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2026-02-232026-11-03
View historical data
DateStars
2026-10-051,883
2026-10-061,884
2026-10-071,885
2026-10-081,887
2026-10-091,887
2026-10-101,887
2026-10-111,888
2026-10-121,890
2026-10-131,890
2026-10-141,891
2026-10-151,893
2026-10-161,893
2026-10-171,894
2026-10-181,894
2026-10-191,894
2026-10-201,895
2026-10-211,895
2026-10-221,897
2026-10-231,897
2026-10-241,897
2026-10-251,898
2026-10-261,901
2026-10-271,901
2026-10-281,902
2026-10-291,902
2026-10-301,904
2026-10-311,904
2026-11-011,903
2026-11-021,904
2026-11-031,904

Get the project

git clone https://github.com/petergpt/bullshit-benchmark.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.