Skip to content

Benchmark

Amharic RAG QA p-value vs Qwen2.5-0.5B no-retrieval baseline (BM25 RAG)

Multilingual benchmarks compare model performance across languages.

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
0.00374
Min

Results

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

ModelScore
Qwen2.5 0.5b Instructfp16, BM25 retrieval, top-3 passages· Amharic-LLM-RAG-Benchmark data docs0.00374

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).