Skip to content

Benchmark

Bridging the Gap Winogrande Afrikaans (af) cultural appropriateness target-language lift (QA Pairs with Only “good” Quality Annotations)

Multilingual benchmarks compare model performance across languages.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

6
Mean
5.6
Median
0.942
Std dev
5.1
10th percentile
7.3
90th percentile
5.1
Min
5.17.3
The band covers the middle 80% of scores. The line marks the median.

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

ModelScore
GPT 4otable: A.19, section: E, language: af· Bridging the Gap (arXiv:2412.12417v1) data5.6
GPT-3.5 Turbotable: A.19, section: E, language: af· Bridging the Gap (arXiv:2412.12417v1) data5.1
GPT-4 Turbotable: A.19, section: E, language: af· Bridging the Gap (arXiv:2412.12417v1) data7.3

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)