OLMo-2-0325-32B: benchmark results
Provider: Allen AI. Released 2025-03-13. Access: Open.
Aggregate Rating 1496 ± 35, rank #2427 of 10916 rated models, from 105 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Spanish NLU - MLQA ES | 71.72 | Character F1 (%) | 99.8 |
| EuroEval French NLU - FQuAD | 77.33 | Character F1 (%) | 99.2 |
| EuroEval Dutch NLU - SQuAD NL | 85.36 | Character F1 (%) | 99.1 |
| EuroEval English NLU - SQuAD | 90.77 | Character F1 (%) | 99.1 |
| EuroEval Norwegian NLU - Norquad | 76.38 | Character F1 (%) | 97.6 |
| EuroEval German NLU - Germanquad | 68.42 | Character F1 (%) | 96.4 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 78.06 | Character F1 (%) | 95.5 |
| EuroEval Icelandic NLU - NQII | 58.36 | Character F1 (%) | 92.2 |
| EuroEval Italian NLU - SQuAD IT | 74.23 | Character F1 (%) | 91.8 |
| EuroEval Finnish NLU - Scandisent FI | 92.42 | Matthews correlation coefficient (%) | 91.5 |
| EuroEval French NLU - Allocine | 95.59 | Matthews correlation coefficient (%) | 91 |
| EuroEval Finnish NLU - Tydiqa FI | 73.13 | Character F1 (%) | 90.9 |
Interactive version: theaggregate.ai/model?slug=olmo-2-0325-32b · How It Works · Data refreshed daily, snapshot 2026-11-08.