OLMo 3 7B Instruct — benchmark results
Allen AI OLMo 3 7B instruction-tuned checkpoint. Provider: Allen AI. Released 2025-11-20. Access: Open.
Unified ELO 1408 ± 10, rank #1182 of 1776 rated models, from 333 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Portuguese NLU - ScaLA PT | 27.42 | Linguistic acceptability Score (%) | 82.5 |
| EuroEval English NLU - ScaLA EN | 52.13 | Linguistic acceptability Score (%) | 78.4 |
| EuroEval Italian NLU - ScaLA IT | 29.13 | Linguistic acceptability Score (%) | 76 |
| EuroEval Polish Summarization - PSC | 22.96 | Score (%) | 70.7 |
| EuroEval Dutch Summarization - Wiki Lingua NL | 33.57 | Score (%) | 70 |
| EuroEval Catalan Summarization - Dacsa CA | 34.5 | Score (%) | 63.6 |
| EuroEval French NLU - ScaLA FR | 37.65 | Linguistic acceptability Score (%) | 61.7 |
| EuroEval Spanish NLU - ScaLA ES | 21.12 | Linguistic acceptability Score (%) | 59.9 |
| Medmarks - MedHallu Hard | 45.94 | Score (%) | 58.6 |
| EuroEval Catalan NLU - ScaLA CA | 12.47 | Linguistic acceptability Score (%) | 58.3 |
| EuroEval Bosnian Summarization - LR SUM BS | 27.01 | Score (%) | 57.2 |
| EuroEval Ukrainian Summarization - LR SUM UK | 26.96 | Score (%) | 56.6 |
Interactive version: theaggregate.ai/model?slug=olmo-3-7b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.