Skip to content

Benchmark

Bridging the Gap Winogrande Amharic (am) culturally appropriate subset, English evaluation (QA Pairs with at Least One “good” Quality Annotation)

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

74.8%
Mean
82.5%
Median
11.4%
Std dev
58.7%
10th percentile
83.2%
90th percentile
58.7%
Min
58.7%83.2%
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: C, language: am· Bridging the Gap (arXiv:2412.12417v1) data83.2%
GPT-3.5 Turbotable: A.18, section: C, language: am· Bridging the Gap (arXiv:2412.12417v1) data58.7%
GPT-4 Turbotable: A.18, section: C, language: am· Bridging the Gap (arXiv:2412.12417v1) data82.5%

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)