ALIA-40B: benchmark results
Provider: BSC. Released 2025-06-01. Access: Open.
Aggregate Rating 1447 ± 26, rank #3888 of 10916 rated models, from 239 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Ukrainian NLU - Cross Domain UK Reviews | 63.15 | Matthews correlation coefficient (%) | 95 |
| EuroEval Hungarian NLU - MultiWikiQA HU | 67.39 | Character F1 (%) | 93.1 |
| EuroEval Estonian NLU - Grammar ET | 45.27 | Matthews correlation coefficient (%) | 92.4 |
| EuroEval Polish NLU - PoQuAD | 59.39 | Character F1 (%) | 91 |
| EuroEval Czech NLU - CSFD Sentiment | 60.92 | Matthews correlation coefficient (%) | 89.5 |
| EuroEval Lithuanian NLU - MultiWikiQA LT | 69.28 | Character F1 (%) | 89.5 |
| EuroEval Romanian NLU - MultiWikiQA RO | 73.24 | Character F1 (%) | 89.3 |
| EuroEval Latvian NLU - MultiWikiQA LV | 66.9 | Character F1 (%) | 89.2 |
| EuroEval Finnish NLU - Tydiqa FI | 72.03 | Character F1 (%) | 88.5 |
| EuroEval Estonian NLU - MultiWikiQA ET | 69.89 | Character F1 (%) | 86.7 |
| EuroEval Norwegian NLU - Norquad | 72.27 | Character F1 (%) | 86.4 |
| EuroEval German NLU - Germanquad | 64.16 | Character F1 (%) | 86.2 |
Interactive version: theaggregate.ai/model?slug=alia-40b · How It Works · Data refreshed daily, snapshot 2026-11-08.