Benchmark
Estonian Native Benchmark grammar correction Levenshtein similarity (instruction-tuned models)
Multilingual benchmarks compare model performance across languages. Higher scores are better.
- Models and systems measured
- 26
- Scores recorded
- 26
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 0.243
- Mean
- 0.248
- Median
- 0.072
- Std dev
- 0.187
- 10th percentile
- 0.321
- 90th percentile
- 0.06
- 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 |
|---|---|
| Claude Sonnet 3.7instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.391 |
| Claude Sonnet 4instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.236 |
| Deepseek V3 (671B-A37B)instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.256 |
| EuroLLM-9B-Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.248 |
| Gemini 2.0 Flashinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.282 |
| Gemini 2.5 Proinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.321 |
| Gemma-2-27B-Itinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.223 |
| Gemma-2-9B-Itinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.182 |
| Gemma-3 27B Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.226 |
| Gemma-3-12b-Itinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.197 |
| GPT-4oinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.395 |
| GPT-4o Miniinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.321 |
| GPT-5instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.313 |
| GPT-OSS-120Binstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.194 |
| Kimi-K2-0905 (1000B-A32B)instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.27 |
| Llama-3.1 405B Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.286 |
| Llama-3.1 70B Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.199 |
| Llama-3.1 8B EstLLM-0825instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.275 |
| Llama-3.1 8B Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.189 |
| Llama-4 Maverick (400B-A17B)instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.261 |
| Llama-4 Scout (109B-A17B)instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.27 |
| Mistral Nemo Instruct (12B)instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.187 |
| Qwen2-72B-Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.06 |
| Qwen3-235B-A22B-2507instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.207 |
| Qwen3-4B-Instruct-2507instruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.136 |
| Qwen3-Next-80B-A3B-Instructinstruction-tuned modelstable: 9, setting: instruction-tuned models, task: Grammar· Estonian Native Benchmark (arXiv:2510.21193v2) data | 0.195 |