Great Commission Benchmark — Newsletter, September 2026: New tests, top picks for ministry
Get the GCB digest
For September 2026 publications on the Great Commission Benchmark, we spotlight two models with the strongest overall scores among newly published leaderboard runs.
Great Commission Benchmark — Newsletter, September 2026: New tests, top picks for ministry
For September 2026, Great Commission Benchmark rounds up how leading AI models behave when the prompts sound like real ministry—research, discipleship, evangelism, and integrity under pressure. Below you will find two spotlight models, ranked by overall score, drawn from runs newly published to the public leaderboard in September 2026.
At a glance
- Why read this: Great Commission Benchmark exists so ministry and technical leaders can steward AI with discernment—not trend-chasing.
- What this issue covers: Benchmark runs that reached the public leaderboard among September 2026 publications.
- What to do next: Read the two spotlights, then open the leaderboard or contribute a test run.
Spotlight: two models to watch
These are the two highest-ranked models among new publications in September 2026 by overall score. Each entry shows the overall score (0–100 composite) plus direct links to the benchmark record and any published insight article.
1. aion-labs/aion-3.5
85.0 / 100
Overall score
The model is published by Aion Labs. It was made available publicly September 23, 2026. It performed exceptionally well on the 150 Great Commission Benchmark items we publish, particularly well in Salvation Through Faith and Human Sinfulness.
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...
2. google/gemini-3.8-flash
82.0 / 100
Overall score
The model is published by Google. It was made available publicly September 2, 2026. It performed exceptionally well on the 150 Great Commission Benchmark items we publish, particularly well in Jesus in History and Universal Sin.
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Explore, test, and serve
- Explore the leaderboard: greatcommissionbenchmark.ai/leaderboard
- Read more insights: greatcommissionbenchmark.ai/insights
- Sponsor or run a test: greatcommissionbenchmark.ai/contribute
- Volunteer (moderation / advisory): greatcommissionbenchmark.ai/contribute
- Subscribe for updates: greatcommissionbenchmark.ai/newsletter
“Test everything; hold fast what is good” (1 Thessalonians 5:21)—and keep making disciples (Matthew 28:19–20).
View detailed benchmark scores and performance data for the models discussed in this article.
