Llama-PLLuM-8B-instruct-2512: benchmark results
Provider: Meta.
Aggregate Rating 1493 ± 32, rank #2465 of 10916 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Polish Knowledge Benchmark - Geography | 74.36 | Accuracy (%) | 45.6 |
| Polish Knowledge Benchmark - Theatre | 66.54 | Accuracy (%) | 42.6 |
| Polish Knowledge Benchmark - Film & Theatre | 66.8 | Accuracy (%) | 41.2 |
| Polish Knowledge Benchmark - Polish Symbols | 69.79 | Accuracy (%) | 40.4 |
| Polish Knowledge Benchmark - Law & Administration | 78.59 | Accuracy (%) | 39.7 |
| Polish Knowledge Benchmark - Overall | 70.84 | Accuracy (%) | 36.8 |
| Polish Knowledge Benchmark - Traditions & Customs | 73.1 | Accuracy (%) | 36.8 |
| Polish Knowledge Benchmark - Art | 70.59 | Accuracy (%) | 35.3 |
| Polish Knowledge Benchmark - Cuisine | 74.57 | Accuracy (%) | 35.3 |
| Polish Knowledge Benchmark - History | 74.74 | Accuracy (%) | 35.3 |
| Polish Knowledge Benchmark - Politics & Society | 77.37 | Accuracy (%) | 35.3 |
| Polish Knowledge Benchmark - Military | 74.14 | Accuracy (%) | 34.6 |
Interactive version: theaggregate.ai/model?slug=llama-pllum-8b-instruct-2512 · How It Works · Data refreshed daily, snapshot 2026-11-08.