Skip to content

Benchmark

FormosanBench MT BLEU (Paiwan→Mandarin, 10-shot)

Multilingual benchmarks compare model performance across languages. Higher scores are better.

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

Score distribution

0.004
Mean
0.004
Median
0
Std dev
0.004
10th percentile
0.004
90th percentile
0.0035
Min

Leaderboard

#ModelScore
1mistral-7b-v0.310-shot, 10 in-context examples, Mandarin prompt· FormosanBench (arXiv:2506.21563v1) data0.0035

Data credits: Lin, Chen and Zhang, FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Models, arXiv:2506.21563v1, CC BY 4.0. Scores extracted from Tables 2-4. (licence)