Benchmark
BTZSC
BTZSC is a systematic evaluation benchmark for zero-shot text classification. It assesses dozens of zero-shot classifiers across 22 datasets, covering NLI models, embedding models, and rerankers. The benchmark was published at ICLR 2026.
Timeline (last 90 days)
Sep 23
The BTZSC benchmark evaluated dozens of zero-shot classifiers across 22 datasets, covering NLI models, embedding models, and rerankers, with the associated paper published at ICLR 2026.
Unverified50%
Sep 23
As of now, Jev has not been formally benchmarked within comprehensive evaluation frameworks such as BTZSC.
Expired50%