Skip to content

Benchmark

Amharic RAG QA RAG-effect p-value vs own no-retrieval baseline (hybrid RRF RAG)

Multilingual benchmarks compare model performance across languages.

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

Score distribution

0.015
Mean
0.015
Median
0
Std dev
0.015
10th percentile
0.015
90th percentile
0.015
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, hybrid RRF retrieval, top-3 passages· Amharic-LLM-RAG-Benchmark data docs0.015

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).