InterFLOPBench
Explore score history ↗InterFLOPBench is a benchmark of 90 C kernels and 1,130 test samples for evaluating LLMs on floating-point error classification across six categories: cancellation, comparison, division by zero, overflow, underflow, and NaN.
- Released
- 2026-06-30
- Institutions
- Laboratoire d’informatique Parallélisme Réseaux Algorithmes Distribués
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
InterFLOPBench paper
No reported scores are on record for this benchmark yet.