~ / benchmarks / suites-harnesses / gpqa
GPQA
Graduate-level, Google-proof MCQs; the Diamond subset is the hard tier. Part of the standard MCQ battery used in Jev vs Luna Decisions comparisons.
- section
- Benchmarks
- group
- Suites & harnesses
- source
- github.com
- repo
- idavidrein/gpqa
- stars
- 540 ▕███████░░░░░▏
- 7-day gain
- 0
- forks
- 60
- language
- Jupyter Notebook
- license
- MIT
- last pushed
- sep 30 2024
- added to list
- oct 7
## history
2025-08-24392 → 540 stars2026-10-13