Benchmark
Bridging the Gap Winogrande Xhosa (xh) culturally inappropriate subset, English evaluation (QA Pairs with Only “good” Quality Annotations)
Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.
- Models measured
- 3
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 75.9%
- Mean
- 83.2%
- Median
- 12.5%
- Std dev
- 58.3%
- 10th percentile
- 86.2%
- 90th percentile
- 58.3%
- Min
Results
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model | Score |
|---|---|
| GPT 4otable: A.19, section: D, language: xh· Bridging the Gap (arXiv:2412.12417v1) data | 86.2% |
| GPT-3.5 Turbotable: A.19, section: D, language: xh· Bridging the Gap (arXiv:2412.12417v1) data | 58.3% |
| GPT-4 Turbotable: A.19, section: D, language: xh· Bridging the Gap (arXiv:2412.12417v1) data | 83.2% |
Data credits: Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin and Guillaume Chabot-Couture. Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments, arXiv:2412.12417v1. CC BY 4.0 article numeric/protocol extract, restructured with values unchanged. No task or model rights asserted. (licence)