Skip to content

Benchmark

Bridging the Gap Winogrande translation quality human evaluation share, evaluator 1 Wrong, evaluator 2 Good

Multilingual benchmarks compare model performance across languages. Scores are percentages.

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

Score distribution

2.2%
Mean
2.2%
Median
0%
Std dev
2.2%
10th percentile
2.2%
90th percentile
2.2%
Min

Results

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Human evaluation of Winogrande translationstable: A.10, response: Wrong/Good, statistic: Avg. (%)· Bridging the Gap (arXiv:2412.12417v1) data2.2%

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)