AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
AX-b
AX-b is a broad-coverage diagnostic task, which requires to determine the logical relation between the given sentence pair, with three relations: entailment, contradiction and neutral. This task is selected from a subset of the GLUE broad-coverage diagnostic dataset, mainly used to test the model's understanding ability in grammar, semantics, world knowledge and so on.
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- Not recorded
- Benchmark release
- 2019-05-02
- Collected
- 2026-08-18
- 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.
Original sources
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.