Skip to content

Benchmark

Bridging the Gap MMLU College Medicine Shona (sn) human translation back-translated to English

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

Models measured
6
Scores recorded
6
Sources
1
IQ weight
No weight published

Score distribution

64.8%
Mean
68.8%
Median
8.2%
Std dev
57.2%
10th percentile
76.9%
90th percentile
54.3%
Min
54.3%76.9%
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.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data76.9%
GPT-3.5 Turbotable: A.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data57.2%
GPT-4 Turbotable: A.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data68.8%
Llama 3 70B Instructtable: A.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data71.7%
Llama 3 8B Instructtable: A.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data54.3%
Phi-3 Mini 4K Instructtable: A.12, section: back-translation-accuracy, task: MMLU College Medicine, language: sn, shots: 5· Bridging the Gap (arXiv:2412.12417v1) data60.1%

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)