Fatika01/nigeria-livestock-llm-benchmark

Domaine:

natural language processingagriculture

Type de record:

dataset

Créateur:

Fat

Hôte:

A 420-question benchmark evaluating LLM performance on Nigerian livestock management knowledge, designed to investigate geographic and cultural bias in large language models. Most LLM benchmarks are Western-centric. This dataset targets a critical gap: how well do frontier models perform on domain knowledge specific to sub-Saharan African agricultural contexts?

Fatikafarouq/llm-nigeria-livestock-benchmark

# LLM Nigeria Livestock Benchmark Benchmarking LLM performance on Nigerian indigenous livestock man

Kambaata LLM Cultural Benchmark

Maintenance release for Zenodo archival of the Kambaata LLM Cultural Benchmark. This release contain

rifaasa/hassaniya-llm-benchmark

benchmark of modern LLMs on Hassaniya Arabic dialect » # hassaniya-llm-benchmark Code and evaluati

BehailuBerhanu/kambaata-llm-cultural-benchmark

A 77-item benchmark for evaluating cultural knowledge, hallucination, and epistemic behavior in larg

balusi130/llm-benchmark-east-africa

Benchmarking suite for evaluating LLM reasoning and linguistic accuracy in East African language con

Shadman19/llm-benchmark-low-resource-languages

Evaluating open-source LLMs on Bengali, Swahili and Tamil vs English baseline # 🌍 LLM Benchmark for