Falcon-H1-Tiny-Multilingual-100M-Base: benchmark results
Provider: TII. Released 2026-01-12. Access: Open.
Aggregate Rating 1209 ± 31, rank #9561 of 10916 rated models, from 263 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - ScaLA CA | 0.21 | Matthews correlation coefficient (%) | 35.5 |
| EuroEval Icelandic NLU - ScaLA IS | 0.98 | Matthews correlation coefficient (%) | 35.5 |
| EuroEval Albanian NLU - ScaLA SQ | 0.84 | Matthews correlation coefficient (%) | 29 |
| EuroEval Serbian Summarization - LR SUM SR | 14.88 | chrF3++ (%) | 27.2 |
| EuroEval Czech NLU - CS GEC | 2.81 | Matthews correlation coefficient (%) | 23.9 |
| EuroEval Norwegian Knowledge - Idioms NO | 0.21 | MCC (x100) | 22.8 |
| EuroEval Czech NLU - SQAD | 22.36 | Character F1 (%) | 21.1 |
| EuroEval Spanish NLU - MLQA ES | 29.51 | Character F1 (%) | 20 |
| EuroEval French NLU - FQuAD | 29.75 | Character F1 (%) | 19.7 |
| EuroEval Czech Knowledge | 3.73 | Knowledge Average Score (%) | 19.5 |
| EuroEval Portuguese Common Sense Reasoning | 1.22 | Common Sense Reasoning Average Score (%) | 18.7 |
| EuroEval Croatian NLU - ScaLA HR | 1.4 | Matthews correlation coefficient (%) | 18.6 |
Interactive version: theaggregate.ai/model?slug=falcon-h1-tiny-multilingual-100m-base · How It Works · Data refreshed daily, snapshot 2026-11-08.