Skip to main content
GCB
Great Commission Benchmark
HomeLeaderboardRecent TestsCategoriesInsightsAbout
Subscribe

Get the GCB digest

New model evaluations and insights for Great Commission work. A monthly digest, plus occasional highlights on important model releases.

Subscribe

Platform

  • Methodology
  • Categories
  • FAQ

Community

  • Sponsor a Model Test
  • Support the Project
  • Volunteer

Legal

  • Terms of Service
  • Privacy Policy
  • Tester Agreement

Connect

  • Contact

Disclaimer: This benchmark is for informational purposes only and does not constitute an endorsement or recommendation of any AI model or service.

GCB
Great Commission Benchmark
•

© 2026 All rights reserved.

•

A project of gospelambition.org.

← Back to Leaderboard
microsoft logo

Microsoft

2 models tested on the Great Commission Benchmark

Models Tested
2
Average Score
42.2%
Top Score
48.3%
Microsoft Insights

Great Commission Benchmark — Newsletter, June 2026: New tests, top picks for ministry

Jun 30, 2026

WizardLM-2 8x22B Review

Jun 3, 2026

Phi-4 Mini Instruct Review

Jun 3, 2026

Models

Phi 4
Fair

microsoft/phi-4

Overall Score48.3%
Task
49
Doctrine
42
Worldview
57
Wizardlm 2 8x22b
Poor

microsoft/wizardlm-2-8x22b

Overall Score36.0%
Task
39
Doctrine
18
Worldview
53