polish-gpt2-xl: benchmark results
Provider: Other.
Aggregate Rating 1205 ± 45, rank #9589 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PSC (multiple choice, 5-shot) | 40.21 | Binary F1 (%) | 26 |
| Open PL LLM - KLEJ NER (multiple choice, 5-shot) | 25.17 | Accuracy (%) | 15.6 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 15.17 | Macro F1 (%) | 14.9 |
| Open PL LLM - PPC (multiple choice, 5-shot) | 39.8 | Accuracy (%) | 11.5 |
| Open PL LLM - Multiple Choice | -12.33 | Average Multiple-Choice Score (%) | 10.8 |
| Open PL LLM - EQ-Bench | 0 | EQ-Bench Score | 9.7 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 10.91 | Binary F1 (%) | 9.2 |
| Open PL LLM - RAG | 3.76 | Average RAG Score (%) | 8.7 |
| Open PL LLM - Belebele (multiple choice, 5-shot) | 27.67 | Accuracy (%) | 7.8 |
| Open PL LLM - CBD (generative, 5-shot) | 14.9 | Macro F1 (%) | 7.2 |
| Open PL LLM Leaderboard | -20.83 | Average Score (%) | 6.6 |
| Open PL LLM - PolQA Closed Book (generative, 5-shot) | 3.63 | Levenshtein Similarity (%) | 6.3 |
Interactive version: theaggregate.ai/model?slug=polish-gpt2-xl · How It Works · Data refreshed daily, snapshot 2026-11-08.