🏆 BTZSC Leaderboard

Benchmark for Zero-Shot Text Classification across Cross-Encoders, Embedding Models, Rerankers and LLMs.

📄 Paper | 💻 Eval Harness | 📊 Results Dataset | 🤗 How to Submit

Primary metric: Macro F1 | 22 datasets | 4 task types (Sentiment · Topic · Intent · Emotion)

Search model

Sort by

Order

Model families

Embedding Model NLI Cross-Encoder Reranker Instruction-tuned LLM

Last loaded: 2026-04-05 18:29 UTC · 35 models evaluated · Results sourced from btzsc/btzsc-results