List of leaderboard's and resources that I developed to evaluate LLM's in a Multilingual and Portuguese settings.
Eduardo Garcia
eduagarcia
AI & ML interests
Master in Computer Science at UFG. AI Researcher on CEIA and Data Lawyer.
Recent Activity
updated a Space 21 days ago
eduagarcia/open_pt_llm_leaderboard updated a dataset about 1 month ago
eduagarcia/tokenizer_benchmark_results updated a Space about 1 month ago
eduagarcia/open_pt_llm_leaderboardOrganizations
A daily uploaded list of models with best evaluations on the PT-LLM leaderboard:
-
tiiuae/Falcon-H1-34B-Base
Text Generation • 34B • Updated • 1.19k • 13 -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 78.4k • • 423 -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 13.6M • • 1.17k -
amadeusai/Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct
Text Generation • 73B • Updated • 8 • 2
List of leaderboard's and resources that I developed to evaluate LLM's in a Multilingual and Portuguese settings.
A daily uploaded list of models with best evaluations on the PT-LLM leaderboard:
-
tiiuae/Falcon-H1-34B-Base
Text Generation • 34B • Updated • 1.19k • 13 -
meta-llama/Llama-3.1-70B
Text Generation • 71B • Updated • 78.4k • • 423 -
Qwen/Qwen3-8B
Text Generation • 8B • Updated • 13.6M • • 1.17k -
amadeusai/Amadeus-Verbo-FI-Qwen2.5-72B-PT-BR-Instruct
Text Generation • 73B • Updated • 8 • 2
Related resources to the paper RoBERTaLexPT: A Legal RoBERTa Model pretrained with deduplication for Portuguese