gervasio-8B-portuguese-ptpt-decoder: benchmark results
Provider: Other.
Aggregate Rating 1430 ± 34, rank #4641 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ALBA - Word Plays | 17 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 57.1 |
| ALBA - Phonetics and Phonology | 15 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 50 |
| ALBA - Discourse Analysis | 61.8 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 35.7 |
| ALBA - Language Variety | 29 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 35.7 |
| ALBA - Morphology | 39.5 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 35.7 |
| P3B3 (pt-BR Prompt) | 11.1 | Variety score (0-100), where 0 is Brazilian and 100 European | 31.6 |
| ALBA | 31.1 | Mean judge score (0-100) over ALBA's 800 expert-written open | 28.6 |
| ALBA - Syntax | 38.3 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 28.6 |
| ALBA - Culture-bound Semantics | 22.8 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 14.3 |
| ALBA - Lexicology | 25.8 | Mean judge score (0-100) on ALBA's 100 expert-written pt-PT | 7.1 |
Interactive version: theaggregate.ai/model?slug=gervasio-8b-portuguese-ptpt-decoder · How It Works · Data refreshed daily, snapshot 2026-11-08.