Baguettotron: benchmark results
Provider: Pleias. Released 2025-11-10.
Aggregate Rating 1187 ± 33, rank #9685 of 10916 rated models, from 263 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Polish Summarization - PSC | 21.58 | chrF3++ (%) | 49.7 |
| EuroEval Icelandic Common Sense Reasoning | 4.17 | Common Sense Reasoning Average Score (%) | 39.9 |
| EuroEval Catalan NLU - ScaLA CA | 0.65 | Matthews correlation coefficient (%) | 38.4 |
| EuroEval Albanian NLU - ScaLA SQ | 1.4 | Matthews correlation coefficient (%) | 33 |
| EuroEval Faroese NLU - ScaLA FO | 0.81 | Matthews correlation coefficient (%) | 31.6 |
| EuroEval Lithuanian NLU - ScaLA LT | 1.82 | Matthews correlation coefficient (%) | 27.9 |
| EuroEval Serbian Summarization - LR SUM SR | 13.48 | chrF3++ (%) | 26.5 |
| EuroEval Spanish NLU - ScaLA ES | 0.36 | Matthews correlation coefficient (%) | 22.4 |
| EuroEval Latvian NLU - ScaLA LV | 0.46 | Matthews correlation coefficient (%) | 22 |
| EuroEval Latvian Common Sense Reasoning | 1.48 | Common Sense Reasoning Average Score (%) | 21.8 |
| EuroEval Slovene NLU - ScaLA SL | 1.5 | Matthews correlation coefficient (%) | 21.2 |
| EuroEval Czech NLU - CS GEC | 1.87 | Matthews correlation coefficient (%) | 20.2 |
Interactive version: theaggregate.ai/model?slug=baguettotron · How It Works · Data refreshed daily, snapshot 2026-11-08.