PLLuM-12B-instruct: benchmark results
Provider: PLLuM.
Aggregate Rating 1420 ± 29, rank #5169 of 10916 rated models, from 26 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CPTU Bench | 3.09 | Average Score (1-5) | 36.6 |
| Polish Knowledge Benchmark - Law & Administration | 73.54 | Accuracy (%) | 25 |
| Polish Knowledge Benchmark - History | 68.87 | Accuracy (%) | 22.1 |
| Polish Knowledge Benchmark - Cuisine | 66.57 | Accuracy (%) | 18.4 |
| Polish Knowledge Benchmark - Polish Symbols | 60.43 | Accuracy (%) | 18.4 |
| Polish Knowledge Benchmark - Politics & Society | 72.48 | Accuracy (%) | 18.4 |
| Polish Knowledge Benchmark - Religion & Philosophy | 74.43 | Accuracy (%) | 18.4 |
| Polish EQ-Bench | 36.21 | EQ-Bench Score (parseability-adjusted) | 16.8 |
| Polish Knowledge Benchmark - Education & Science | 62.09 | Accuracy (%) | 11.8 |
| Polish Knowledge Benchmark - Film & Theatre | 53.12 | Accuracy (%) | 11.8 |
| Polish Knowledge Benchmark - Geography | 57.74 | Accuracy (%) | 10.3 |
| Polish Knowledge Benchmark - Theatre | 51.92 | Accuracy (%) | 10.3 |
Interactive version: theaggregate.ai/model?slug=pllum-12b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.