EternityYW/Gemini-Commonsense-Evaluation

Official implementation of "Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models"

29
/ 100
Experimental

This project provides a comprehensive evaluation of Gemini Pro's ability to understand and apply common sense in various situations, including those involving both text and images. It takes in specific datasets, prompts, and models, and outputs detailed experimental results and key findings. This is valuable for AI researchers, machine learning engineers, and product managers who are developing or integrating large language models.

No commits in the last 6 months.

Use this if you need to understand how well Gemini Pro and other leading large language models perform on different commonsense reasoning tasks, especially when comparing their capabilities with text-based and visual data.

Not ideal if you are looking for a tool to build or fine-tune your own language models, as this project focuses solely on evaluating existing models.

AI evaluation Large language models Commonsense reasoning Multimodal AI Model comparison
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

37

Forks

2

Language

License

MIT

Last pushed

Jan 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/EternityYW/Gemini-Commonsense-Evaluation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.