Bielik-SOLAR-LIKE-10.7B-Instruct-v0.1: benchmark results
A depth-upscaled release by TeeZee applying the card's stated SOLAR recipe to speakleash/Bielik-7B-Instruct-v0.1. The publisher reports no post-merge fine-tuning at this revision. Provider: TeeZee. Access: Open.
Aggregate Rating 1331 ± 29, rank #8138 of 10916 rated models, from 34 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open PL LLM - PolQA Closed Book (generative, 5-shot) | 64.9 | Levenshtein Similarity (%) | 73.3 |
| Open PL LLM - CBD (multiple choice, 5-shot) | 31.05 | Macro F1 (%) | 72.4 |
| Open PL LLM - CBD (generative, 5-shot) | 31.87 | Macro F1 (%) | 72 |
| Open PL LLM - PolEmo2-IN (multiple choice, 5-shot) | 80.89 | Accuracy (%) | 67.2 |
| Open PL LLM - PolQA Open Book (generative, 5-shot) | 84.14 | Levenshtein Similarity (%) | 65 |
| Open PL LLM - PSC (multiple choice, 5-shot) | 67.82 | Binary F1 (%) | 56.7 |
| Open LLM Leaderboard v1 - GSM8K | 41.47 | Accuracy (%) (5-shot) | 56.4 |
| Open PL LLM - DYK (multiple choice, 5-shot) | 50.52 | Binary F1 (%) | 53.8 |
| Open PL LLM - DYK (generative, 5-shot) | 52.55 | Binary F1 (%) | 53.6 |
| Open PL LLM - 8TAGS (generative, 5-shot) | 72.78 | Accuracy (%) | 52.5 |
| Open PL LLM - Generative | 49.3 | Average Generative Score (%) | 52.4 |
| Open PL LLM - PolEmo2-OUT (generative, 5-shot) | 66.6 | Accuracy (%) | 51.6 |
Interactive version: theaggregate.ai/model?slug=bielik-solar-like-10-7b-instruct-v0-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.