baseline-7-8b_2-3t-tokens_llama: benchmark results
Provider: Other. Released 2025-09-02.
Aggregate Rating 1313 ± 30, rank #8487 of 10916 rated models, from 177 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - Guia CAT | 66.46 | Matthews correlation coefficient (%) | 75.4 |
| EuroEval Dutch Simplification - Duidelijke Taal | 50.78 | Score (%) | 62.5 |
| EuroEval Finnish NLU - Tydiqa FI | 63.16 | Character F1 (%) | 57.9 |
| EuroEval Bulgarian NLU - Cinexio | 30.89 | Matthews correlation coefficient (%) | 53.1 |
| EuroEval Polish NLU - Polemo2 | 83.3 | Matthews correlation coefficient (%) | 52.8 |
| EuroEval Dutch NLU - DBRD | 86.23 | Matthews correlation coefficient (%) | 48.1 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 65.88 | Character F1 (%) | 47 |
| EuroEval Portuguese NLU - SST-2 PT | 75.35 | Matthews correlation coefficient (%) | 46.8 |
| EuroEval Slovene NLU - MultiWikiQA SL | 48.49 | Character F1 (%) | 44.8 |
| EuroEval Polish NLU - PoQuAD | 43.89 | Character F1 (%) | 44.6 |
| EuroEval Catalan NLU | 47.16 | NLU Average Score (%) | 44.5 |
| EuroEval Spanish NLU - MLQA ES | 58.25 | Character F1 (%) | 44.3 |
Interactive version: theaggregate.ai/model?slug=baseline-7-8b-2-3t-tokens-llama · How It Works · Data refreshed daily, snapshot 2026-11-08.