Skip to content

Benchmark

Bridging the Gap Belebele Igbo (ig) human-translation minus back-translation difference

Multilingual benchmarks compare model performance across languages.

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

Score distribution

-10.7
Mean
-12.5
Median
12
Std dev
-21.5
10th percentile
8.5
90th percentile
-23.5
Min
-23.58.5
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.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data8.5
GPT-3.5 Turbotable: A.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data-23.5
GPT-4 Turbotable: A.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data2.2
Llama 3 70B Instructtable: A.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data-17.5
Llama 3 8B Instructtable: A.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data-12.5
Phi-3 Mini 4K Instructtable: A.15, section: back-translation-difference, task: Belebele, language: ig, shots: 0· Bridging the Gap (arXiv:2412.12417v1) data-21.5

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)