Vibhanshu-555/Human-Aligned-LLM-Evaluation-Audit
A data-driven audit of AI judge reliability using MT-Bench human annotations. This project analyzes 3,500+ model comparisons across 6 LLMs and 8 task categories to measure how well GPT-4 evaluations align with human judgment. Includes Python workflow, disagreement metrics, and a Power BI dashboard for insights.
Stars
—
Forks
—
Language
HTML
License
MIT
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Vibhanshu-555/Human-Aligned-LLM-Evaluation-Audit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
EvolvingLMMs-Lab/lmms-eval
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
open-compass/VLMEvalKit
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
vibrantlabsai/ragas
Supercharge Your LLM Application Evaluations 🚀
evalplus/evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Giskard-AI/giskard-oss
🐢 Open-Source Evaluation & Testing library for LLM Agents