multilingual-e5-base: benchmark results
Provider: Microsoft. Released 2022-12-01. Access: Open.
Aggregate Rating 1474 ± 31, rank #2753 of 10916 rated models, from 143 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Catalan NLU - WikiANN CA | 83.02 | Micro F1 excluding MISC (%) | 99.5 |
| EuroEval Estonian NLU - EstNER | 65.16 | Micro F1 excluding MISC (%) | 99.2 |
| EuroEval Bosnian NLU - WikiANN BS | 84.29 | Micro F1 excluding MISC (%) | 99.1 |
| EuroEval Czech NLU - PONER | 70.2 | Micro F1 excluding MISC (%) | 99.1 |
| EuroEval Portuguese NLU - HAREM | 74.56 | Micro F1 excluding MISC (%) | 99.1 |
| EuroEval Albanian NLU - WikiANN SQ | 85.86 | Micro F1 excluding MISC (%) | 99 |
| EuroEval Croatian NLU - WikiANN HR | 80.33 | Micro F1 excluding MISC (%) | 99 |
| EuroEval Greek NLU - ELNER | 82.85 | Micro F1 excluding MISC (%) | 99 |
| EuroEval Lithuanian NLU - WikiANN LT | 75.86 | Micro F1 excluding MISC (%) | 98.7 |
| EuroEval Italian NLU - MultiNERD IT | 86.38 | Micro F1 excluding MISC (%) | 98.6 |
| EuroEval Hungarian NLU - Szeged NER | 91.15 | Micro F1 excluding MISC (%) | 98.5 |
| EuroEval Spanish NLU - CoNLL ES | 83.16 | Micro F1 excluding MISC (%) | 98.5 |
Interactive version: theaggregate.ai/model?slug=multilingual-e5-base · How It Works · Data refreshed daily, snapshot 2026-11-08.