Benchmark
Estonian Native Benchmark declension accuracy (base models)
Multilingual benchmarks compare model performance across languages. Higher scores are better.
- Models and systems measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 0.413
- Mean
- 0.416
- Median
- 0.109
- Std dev
- 0.306
- 10th percentile
- 0.586
- 90th percentile
- 0.268
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Gemma 2 27Bbase modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.505 |
| Gemma 2 9Bbase modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.396 |
| Llama 3.1 70Bbase modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.586 |
| Llama 3.1 8Bbase modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.268 |
| Mistral Nemo Base (12B)base modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.416 |
| Qwen2 72Bbase modelstable: 8, setting: base models, task: Declension· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.306 |