Ahma-2-4B-Instruct: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1375 ± 41, rank #7027 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| EuroEval Finnish NLU - Scandisent FI | 91.13 | Matthews correlation coefficient (%) | 74.2 |
| EuroEval Estonian NLU - Estonian Valence | 45.69 | Matthews correlation coefficient (%) | 52.4 |
| EuroEval Estonian NLU - Grammar ET | 6.59 | Matthews correlation coefficient (%) | 46.2 |
| EuroEval Estonian Knowledge | 5.85 | Knowledge Average Score (%) | 44.7 |
| EuroEval Finnish Common Sense Reasoning | 18.32 | Common Sense Reasoning Average Score (%) | 43 |
| EuroEval Estonian Common Sense Reasoning | 5.07 | Common Sense Reasoning Average Score (%) | 35.5 |
| EuroEval Estonian NLU | 28 | NLU Average Score (%) | 32.9 |
| EuroEval Estonian | 20.49 | Average Score (%) | 32.1 |
| EuroEval Estonian NLU - MultiWikiQA ET | 26.75 | Character F1 (%) | 27 |
| EuroEval Estonian NLU - EstNER | 32.99 | Micro F1 excluding MISC (%) | 26.5 |
| EuroEval Finnish | 33.03 | Average Score (%) | 21.7 |
| EuroEval Finnish NLU | 36.71 | NLU Average Score (%) | 18.5 |
Interactive version: theaggregate.ai/model?slug=ahma-2-4b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.