Skip to content

Benchmark

Bridging the Gap Winogrande Sesotho (st) cultural appropriateness English lift (QA Pairs with at Least One “good” Quality Annotation)

Multilingual benchmarks compare model performance across languages.

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

Score distribution

2.1
Mean
2.8
Median
1.5
Std dev
0.1
10th percentile
3.5
90th percentile
0.1
Min
0.13.5
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.18, section: F, language: st· Bridging the Gap (arXiv:2412.12417v1) data0.1
GPT-3.5 Turbotable: A.18, section: F, language: st· Bridging the Gap (arXiv:2412.12417v1) data3.5
GPT-4 Turbotable: A.18, section: F, language: st· Bridging the Gap (arXiv:2412.12417v1) data2.8

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)