OLMo-2-1124-13B: benchmark results
Provider: Allen AI. Released 2024-11-26. Access: Open.
Aggregate Rating 1375 ± 27, rank #6992 of 10916 rated models, from 132 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval English NLU - SQuAD | 90.85 | Character F1 (%) | 99.4 |
| EuroEval Spanish NLU - MLQA ES | 69.89 | Character F1 (%) | 98.3 |
| EuroEval French NLU - FQuAD | 76.03 | Character F1 (%) | 97.1 |
| EuroEval Dutch NLU - SQuAD NL | 82.48 | Character F1 (%) | 96.9 |
| EuroEval German NLU - Germanquad | 68.27 | Character F1 (%) | 95.6 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 77.15 | Character F1 (%) | 93.1 |
| EuroEval French NLU - Allocine | 95.75 | Matthews correlation coefficient (%) | 92 |
| EuroEval Finnish NLU - Tydiqa FI | 72.75 | Character F1 (%) | 90.1 |
| EuroEval Italian NLU - SQuAD IT | 72.94 | Character F1 (%) | 87.8 |
| EuroEval Norwegian NLU - Norquad | 72.22 | Character F1 (%) | 85.9 |
| EuroEval English NLU - SST-5 | 68.25 | Matthews correlation coefficient (%) | 81.4 |
| EuroEval Swedish NLU - Swerec | 78.01 | Matthews correlation coefficient (%) | 81.3 |
Interactive version: theaggregate.ai/model?slug=olmo-2-1124-13b · How It Works · Data refreshed daily, snapshot 2026-11-08.