OLMo 3 7B Instruct: benchmark results
Allen AI OLMo 3 7B instruction-tuned checkpoint. Provider: Allen AI. Released 2025-11-20. Access: Open.
Aggregate Rating 1403 ± 13, rank #1218 of 1656 rated models, from 475 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UnpredictaBench - Shuffling | 36.84 | KS@100 (%): share of the 19 Shuffling problems (random order | 92.1 |
| CringeBench | 0.69 | Cringe Score (0-10, lower is better) | 87.9 |
| EuroEval Portuguese NLU - ScaLA PT | 27.42 | Matthews correlation coefficient (%) | 82.5 |
| MERA Code - CodeCorrectness | 81.56 | Accuracy (%) | 80 |
| EuroEval English NLU - ScaLA EN | 52.13 | Matthews correlation coefficient (%) | 78.4 |
| EuroEval Italian NLU - ScaLA IT | 29.13 | Matthews correlation coefficient (%) | 76 |
| EuroEval Polish Summarization - PSC | 22.96 | chrF3++ (%) | 70.7 |
| EuroEval Dutch Summarization - Wiki Lingua NL | 33.57 | chrF3++ (%) | 70 |
| IntentGrasp - Writing | 27.57 | Instance F1 (%) on the Writing (W) domain of the 12,909-item | 70 |
| MERA - LCS | 16 | Accuracy (%) | 64.3 |
| EuroEval Catalan Summarization - Dacsa CA | 34.5 | chrF3++ (%) | 63.6 |
| EuroEval French NLU - ScaLA FR | 37.65 | Matthews correlation coefficient (%) | 61.7 |
Interactive version: theaggregate.ai/model?slug=olmo-3-7b-instruct · How It Works · Data refreshed daily, snapshot 2026-10-20.