Marco-Mini-Global-Base: benchmark results
Provider: Alibaba. Released 2026-04-03. Access: Open.
Aggregate Rating 1192 ± 33, rank #9660 of 10916 rated models, from 263 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - ScaLA CA | 1.07 | Matthews correlation coefficient (%) | 40.8 |
| EuroEval Spanish NLU - ScaLA ES | 1.93 | Matthews correlation coefficient (%) | 31.6 |
| EuroEval Greek Common Sense Reasoning | 3.53 | Common Sense Reasoning Average Score (%) | 30.1 |
| EuroEval Italian Common Sense Reasoning | 3.49 | Common Sense Reasoning Average Score (%) | 22.6 |
| EuroEval Croatian Common Sense Reasoning | 1.28 | Common Sense Reasoning Average Score (%) | 22.3 |
| EuroEval Bulgarian NLU - ScaLA BG | 3.35 | Matthews correlation coefficient (%) | 21.3 |
| EuroEval Czech Knowledge | 8.55 | Knowledge Average Score (%) | 21 |
| EuroEval Italian NLU - ScaLA IT | 1.88 | Matthews correlation coefficient (%) | 21 |
| EuroEval Portuguese Common Sense Reasoning | 1.46 | Common Sense Reasoning Average Score (%) | 21 |
| EuroEval Catalan Common Sense Reasoning | 1.43 | Common Sense Reasoning Average Score (%) | 20.7 |
| EuroEval Norwegian Knowledge - NRK Quiz QA | 5.09 | MCC (x100) | 20.6 |
| EuroEval Swedish Common Sense Reasoning | 2.21 | Common Sense Reasoning Average Score (%) | 19.4 |
Interactive version: theaggregate.ai/model?slug=marco-mini-global-base · How It Works · Data refreshed daily, snapshot 2026-11-08.