Bielik-11B-v3.0-Instruct: benchmark results
Provider: SpeakLeash. Released 2025-07-30. Access: Open.
Aggregate Rating 1567 ± 15, rank #1449 of 10916 rated models, from 333 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - CBD (generative, 5-shot) | 43.52 | Macro F1 (%) | 99.1 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 44.07 | Macro F1 (%) | 99.1 |
| EuroEval Serbian NLU - MMS SR | 52.23 | Matthews correlation coefficient (%) | 99 |
| EuroEval Finnish NLU - Scandisent FI | 93.5 | Matthews correlation coefficient (%) | 98.9 |
| Open PL LLM - 8TAGS (generative, 5-shot) | 79.96 | Accuracy (%) | 98.3 |
| Open PL LLM - PolQA Closed Book (generative, 5-shot) | 84.42 | Levenshtein Similarity (%) | 98.1 |
| EuroEval Ukrainian NLU - Cross Domain UK Reviews | 63.76 | Matthews correlation coefficient (%) | 97.5 |
| Open PL LLM - 8TAGS (multiple choice, 5-shot) | 80.19 | Accuracy (%) | 97.3 |
| EuroEval Norwegian NLU - Norec | 63.19 | Matthews correlation coefficient (%) | 96.5 |
| Open PL LLM Leaderboard | 65.93 | Average Score (%) | 96.5 |
| EuroEval Swedish NLU - Swerec | 80.14 | Matthews correlation coefficient (%) | 96.4 |
| EuroEval Spanish NLU - ScaLA ES | 51.19 | Matthews correlation coefficient (%) | 96.1 |
Interactive version: theaggregate.ai/model?slug=bielik-11b-v3-0-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.