Olmo-3-1025-7B: benchmark results
Provider: Allen AI. Released 2025-11-20. Access: Open.
Aggregate Rating 1397 ± 29, rank #6267 of 10916 rated models, from 264 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval English NLU - SQuAD | 90.07 | Character F1 (%) | 98.5 |
| EuroEval French NLU - FQuAD | 76.1 | Character F1 (%) | 97.9 |
| EuroEval Spanish NLU - MLQA ES | 68.85 | Character F1 (%) | 94.9 |
| EuroEval German NLU - Germanquad | 68.04 | Character F1 (%) | 94.4 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 77.27 | Character F1 (%) | 93.5 |
| EuroEval Catalan NLU - MultiWikiQA CA | 74.93 | Character F1 (%) | 91.5 |
| EuroEval German Summarization - Mlsum DE | 36.73 | chrF3++ (%) | 87.8 |
| EuroEval Finnish NLU - Tydiqa FI | 71.58 | Character F1 (%) | 87.7 |
| EuroEval Dutch NLU - SQuAD NL | 78.14 | Character F1 (%) | 86.7 |
| EuroEval Polish NLU - PoQuAD | 57.45 | Character F1 (%) | 86.5 |
| EuroEval Bosnian NLU - Multi Wiki QA BS | 68.66 | Character F1 (%) | 82.9 |
| EuroEval Romanian NLU - MultiWikiQA RO | 70.82 | Character F1 (%) | 82 |
Interactive version: theaggregate.ai/model?slug=olmo-3-1025-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.