Six Navers Lab / Einsia benchmarks and the work they test
Compare the tasks, scoring and evidence behind six Einsia benchmarks, with complete Radar detail pages and original references.
Model reports
NAFBench
Solver-certified normal logic programs verbalized into natural language, each labelled under four negation semantics (SLDNF, well-founded, and credulous and skeptical stable-model reasoning) that can disagree on the same instance. A score without the semantics named is not comparable. Models are also sensitive to rule order. The leaderboard's hidden test split (Hugging Face qbao775/naf-bench, as described by the repository README at revision 83ede91) has 495 rows drawn from only 77 programs, so the effective sample is the program, not the row. The arXiv v1 appendix describes an earlier 385-prompt evaluation set over 77 programs, so a paper number and a leaderboard number are not on the same split.
Evidence available for this benchmark
Numeric results have not been collected for this source record. Use the paper, code or dataset below to check the task and experiments; this does not imply that the original work contains no results.
Start with these resources
Evaluation context and evidence
- Source
- Model reports
- Publisher
- Not recorded
- Benchmark release
- 2026-09-23
- Collected
- Not recorded
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.