BTZSC - LLM: leaderboard
BTZSC LLM slice measures zero-shot text classification macro-F1 for instruction-tuned language models.
Metric: Macro-F1 (%). Source: huggingface.co. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mistral-Nemo-Instruct-2407 | 66.97 | |
| 2 | Qwen3-8B | 66.49 | |
| 3 | Qwen3-4B | 64.86 | |
| 4 | Phi-4-mini-instruct | 43.09 | |
| 5 | Llama-3.2-3B-Instruct | 43.02 | |
| 6 | gemma-3-1b-it | 35.91 | |
| 7 | gemma-3-270m-it | 27.94 |
Interactive version: theaggregate.ai/benchmark?slug=btzsc-llm · How It Works · Data refreshed daily, snapshot 2026-10-20.