Model Responses with Accuracy, Confidence, and Citation Validity Scores

A 51.0 KB Excel file contains a multidimensional evaluation dataset. It includes model responses, accuracy scores, confidence ratings, and citation validity results. The dataset was authored by Prita Abhay Dhaimade and last updated on May 29, 2026.

Use Cases

• Benchmarking model accuracy based on the provided accuracy scores
• Analyzing the relationship between model confidence ratings and actual performance
• Evaluating the validity of citations generated by AI models
• Comparing multiple model responses across the same evaluation criteria

Strengths

• Dataset is licensed under CC-BY-4.0, allowing for broad reuse and sharing.
• It consolidates multiple evaluation metrics—accuracy, confidence, and citation validity—into a single resource.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited; actual data quality requires manual inspection.

Provenance

Source

Prita Abhay Dhaimade via figshare

Freshness

Last updated 2026-05-29 17:32:19; freshness should be verified.