Skip to content

Benchmark

Bridging the Gap Belebele 11-language African average

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models and systems measured
7
Scores recorded
7
Sources
1
IQ weight
No weight published

Score distribution

45.2%
Mean
36.3%
Median
18.1%
Std dev
32.2%
10th percentile
69.6%
90th percentile
25%
Min
25%76%
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.

Model or systemScore
GPT 4otable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data76%
GPT-3.5 Turbotable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data36.2%
GPT-4 Turbotable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data69.6%
Llama 3 70B Instructtable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data41.2%
Llama 3 8B Instructtable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data36.3%
Phi-3 Mini 4K Instructtable: 1, section: average, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data32.2%
Randomtable: 1, section: average, control: Random, task: Belebele· Bridging the Gap (arXiv:2412.12417v1) data25%

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)