Bielik-7B-v0.1: benchmark results
Provider: SpeakLeash. Access: Open.
Aggregate Rating 1363 ± 42, rank #7364 of 10916 rated models, from 28 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PolQA Open Book (generative, 5-shot) | 88.39 | Levenshtein Similarity (%) | 83.6 |
| Open PL LLM - PolQA Closed Book (generative, 5-shot) | 74.97 | Levenshtein Similarity (%) | 81.3 |
| Open PL LLM - 8TAGS (multiple choice, 5-shot) | 73.56 | Accuracy (%) | 56.7 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 21.34 | Macro F1 (%) | 46.4 |
| Open PL LLM - PolEmo2-OUT (multiple choice, 5-shot) | 66.8 | Accuracy (%) | 45.6 |
| Open PL LLM - RAG | 53.96 | Average RAG Score (%) | 45.1 |
| Open PL LLM - PolEmo2-IN (generative, 5-shot) | 72.71 | Accuracy (%) | 43.4 |
| Open PL LLM - Generative | 42.31 | Average Generative Score (%) | 41.3 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 64.98 | Accuracy (%) | 39.7 |
| Open PL LLM - EQ-Bench | 20.85 | EQ-Bench Score | 38.7 |
| Open PL LLM Leaderboard | 34.34 | Average Score (%) | 36.7 |
| Open PL LLM - CBD (generative, 5-shot) | 19.93 | Macro F1 (%) | 35.2 |
Interactive version: theaggregate.ai/model?slug=bielik-7b-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.