Qra-1B: benchmark results
Provider: Other.
Aggregate Rating 1213 ± 46, rank #9530 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PSC (multiple choice, 5-shot) | 41.18 | Binary F1 (%) | 27.3 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 27.5 | Binary F1 (%) | 20.6 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 15.5 | Macro F1 (%) | 19.5 |
| Open PL LLM - PPC (generative, 5-shot) | 42.3 | Accuracy (%) | 18.8 |
| Open PL LLM - Multiple Choice | -6.79 | Average Multiple-Choice Score (%) | 16.8 |
| Open PL LLM - Generative | 5.77 | Average Generative Score (%) | 16.4 |
| Open PL LLM Leaderboard | 0.31 | Average Score (%) | 16.4 |
| Open PL LLM - PSC (generative, 5-shot) | 61.63 | Binary F1 (%) | 15.3 |
| Open PL LLM - RAG | 15.17 | Average RAG Score (%) | 14.3 |
| Open PL LLM - PolQA Closed Book (generative, 5-shot) | 12.36 | Levenshtein Similarity (%) | 13.8 |
| Open PL LLM - KLEJ NER (generative, 5-shot) | 27.02 | Accuracy (%) | 13.7 |
| Open PL LLM - PolEmo2-IN (generative, 5-shot) | 38.23 | Accuracy (%) | 13.4 |
Interactive version: theaggregate.ai/model?slug=qra-1b · How It Works · Data refreshed daily, snapshot 2026-11-08.