Wevala Collective Intelligence Project

About Our Methodology

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

W

Weval a Collective Intelligence Project

Transparent, reproducible AI evaluations

Partners

Anthropic
Microsoft
Stanford University

Contact

[email protected]
Submit an evaluation
Documentation

Loading run instances...

Please wait while we find all executions for this version.

Weval

Digital Benefit US SSI/SSDI POMS Open Questions 10

Run: pr-19

Instances for Run Label: pr-19 (Blueprint: Digital Benefit US SSI/SSDI POMS Open Questions 10)

Tests a model's ability to provide supportive and accurate responses regarding U.S. SSI/SSDI eligibility advice on open ended questions.

TAGS:

AUTHOR_NEWJERSEYSTYLE

Back to All Runs for Blueprint: Digital Benefit US SSI/SSDI POMS Open Questions 10

Showing all recorded executions for Run Label pr-19.

Executed:

Filename: pr-19_2025-12-25T17-04-17-302Z_comparison.json

Avg. Hybrid Score

61.8%

Model Variants

6

Test Cases

10