Skip to content

Benchmark

Amharic RAG QA SacreBLEU (BM25 RAG)

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

1.3
Mean
1.3
Median
0
Std dev
1.3
10th percentile
1.3
90th percentile
1.3
Min

Leaderboard

#ModelScore
1Qwen2.5 0.5b Instructfp16, BM25 retrieval, top-3 passages· Amharic-LLM-RAG-Benchmark data docs1.3

Data credits: Amharic-LLM-RAG-Benchmark by Bedru Yimam Ahmed. Public numeric results; no results licence stated (repository MIT covers code only; dataset and model licences not borrowed).