Olmo-3-7B-Instruct-SFT: benchmark results
Provider: Allen AI. Released 2025-11-20. Access: Open.
Aggregate Rating 1343 ± 28, rank #7893 of 10916 rated models, from 264 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval English NLU - ScaLA EN | 50.56 | Matthews correlation coefficient (%) | 73.3 |
| EuroEval Portuguese NLU - ScaLA PT | 21.51 | Matthews correlation coefficient (%) | 72.7 |
| EuroEval Italian NLU - ScaLA IT | 24.42 | Matthews correlation coefficient (%) | 60.7 |
| EuroEval Catalan NLU - ScaLA CA | 10.34 | Matthews correlation coefficient (%) | 56.4 |
| EuroEval Bosnian NLU - Multi Wiki QA BS | 61.42 | Character F1 (%) | 52.4 |
| EuroEval Spanish NLU - ScaLA ES | 16.03 | Matthews correlation coefficient (%) | 51.6 |
| EuroEval Ukrainian Summarization - LR SUM UK | 25.72 | chrF3++ (%) | 48.3 |
| EuroEval Serbian Summarization - LR SUM SR | 24.7 | chrF3++ (%) | 44.9 |
| EuroEval Italian NLU - Sentipolc16 | 46.98 | Matthews correlation coefficient (%) | 44.1 |
| EuroEval Icelandic NLU - ScaLA IS | 1.84 | Matthews correlation coefficient (%) | 43.7 |
| EuroEval Lithuanian NLU - MultiWikiQA LT | 51.11 | Character F1 (%) | 43.7 |
| EuroEval Romanian NLU - MultiWikiQA RO | 59.29 | Character F1 (%) | 43.7 |
Interactive version: theaggregate.ai/model?slug=olmo-3-7b-instruct-sft · How It Works · Data refreshed daily, snapshot 2026-11-08.