pllum-12B-nc-instruct-250715: benchmark results
Provider: PLLuM.
Aggregate Rating 1423 ± 25, rank #5042 of 10916 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CPTU Bench | 3.33 | Average Score (1-5) | 47 |
| Belebele European - German | 68.89 | Accuracy (%, 0-shot) | 42.9 |
| Belebele European - Bulgarian | 60 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - Czech | 63 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - French | 70.78 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - Italian | 67.67 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - Portuguese | 67.44 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - Slovak | 59.78 | Accuracy (%, 0-shot) | 39.3 |
| Belebele European - Spanish | 67.33 | Accuracy (%, 0-shot) | 39.3 |
| FLORES European Languages Leaderboard - BLEU | 11.98 | Average BLEU | 36.8 |
| Belebele European - Greek | 59.33 | Accuracy (%, 0-shot) | 35.7 |
| Belebele European - Polish | 66.11 | Accuracy (%, 0-shot) | 35.7 |
Interactive version: theaggregate.ai/model?slug=pllum-12b-nc-instruct-250715 · How It Works · Data refreshed daily, snapshot 2026-11-08.