PLLuM-12B-nc-chat: benchmark results
PLLuM's 12B nc-chat (2412), a chat model in the Polish-focused PLLuM family, released for non-commercial use. Provider: PLLuM. Released 2025-02-24. Access: Open.
Aggregate Rating 1429 ± 21, rank #1101 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 43.54 | Score | 74.6 |
| LLMZSZL Leaderboard | 53.4 | Score | 69.4 |
| MT-Bench PL - Humanities | 9.5 | Judge Score (0-10) | 67.3 |
| MT-Bench PL - STEM | 9.1 | Judge Score (0-10) | 63.3 |
| PLCC - Art & Entertainment | 59 | Accuracy (%) | 49.6 |
| MT-Bench PL - Overall | 6.47 | Judge Score (0-10) | 46.9 |
| PLCC - Culture & Tradition | 65 | Accuracy (%) | 42.9 |
| CPTU Bench | 3.15 | Average Score (1-5) | 40.1 |
| MT-Bench PL - Writing | 7.55 | Judge Score (0-10) | 39.8 |
| Open LLM Leaderboard - GPQA | 28.27 | Score | 37.6 |
| PLCC - Geography | 70 | Accuracy (%) | 36.3 |
| PLCC - Vocabulary | 52 | Accuracy (%) | 36.1 |
Interactive version: theaggregate.ai/model?slug=pllum-12b-nc-chat · How It Works · Data refreshed daily, snapshot 2026-10-20.