Benchmark
Macedonian LM Evaluation Harness WinoGrande accuracy
Multilingual benchmarks compare model performance across languages. Higher scores are better.
- Models and systems measured
- 12
- Scores recorded
- 12
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 0.582
- Mean
- 0.606
- Median
- 0.042
- Std dev
- 0.519
- 10th percentile
- 0.63
- 90th percentile
- 0.509
- 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 |
|---|---|
| domestic-yak-basetable: 4, task: WinoGrande, stage: domestic-yak-base· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.63 |
| domestic-yak-instructtable: 4, task: WinoGrande, stage: domestic-yak-instruct· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.63 |
| domestic-yak†8Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.627 |
| Llama 3.18Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.568 |
| Llama 3.1Llama-3.1-8B-Instructtable: 4, task: WinoGrande, stage: Llama 3.1· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.57 |
| Llama 3.21Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.509 |
| Llama 3.370Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.609 |
| Mistral7Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.561 |
| Mistral Nemo12Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.606 |
| MKLLM†7Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.615 |
| Phi-3.5-mini3.8Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.519 |
| Qwen2.57Btable: 3, task: WinoG· Macedonian Foundation Model (arXiv:2506.09560v1) data | 0.535 |
Data credits: Stefan Krsteski, Matea Tashkovska, Borjan Sazdov, Hristijan Gjoreski and Branislav Gerazov. Towards Open Foundation Language Model and Corpus for Macedonian, arXiv:2506.09560v1. CC BY 4.0 article numeric/protocol extract; restructured, printed values unchanged. No task, corpus, weight or raw survey rights asserted. (licence)