Olmo-3-1125-32B: benchmark results
Provider: Allen AI. Released 2025-11-20. Access: Open.
Aggregate Rating 1456 ± 28, rank #3517 of 10916 rated models, from 256 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Bosnian NLU - Multi Wiki QA BS | 78.64 | Character F1 (%) | 100 |
| EuroEval Catalan NLU - MultiWikiQA CA | 80.41 | Character F1 (%) | 100 |
| EuroEval Danish NLU - Multi Wiki QA DA | 83.76 | Character F1 (%) | 100 |
| EuroEval English NLU - SQuAD | 93.12 | Character F1 (%) | 100 |
| EuroEval French NLU - FQuAD | 78.22 | Character F1 (%) | 100 |
| EuroEval Norwegian NLU - Norquad | 82.14 | Character F1 (%) | 100 |
| EuroEval Polish NLU - PoQuAD | 71 | Character F1 (%) | 100 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 81.39 | Character F1 (%) | 100 |
| EuroEval Romanian NLU - MultiWikiQA RO | 80.55 | Character F1 (%) | 100 |
| EuroEval Slovene NLU - MultiWikiQA SL | 77.08 | Character F1 (%) | 100 |
| EuroEval Swedish NLU - Multi Wiki QA SV | 84.22 | Character F1 (%) | 100 |
| EuroEval German NLU - Germanquad | 72.36 | Character F1 (%) | 99.7 |
Interactive version: theaggregate.ai/model?slug=olmo-3-1125-32b · How It Works · Data refreshed daily, snapshot 2026-11-08.