Report
Compare every model's scripture fidelity.
The Model Summary Report delivers a comprehensive performance overview of all registered LLMs. Compare average fidelity scores, the perfect match rate, provider breakdowns, and campaign-level results in a single view — so you can make informed decisions about which models to trust for scripture retrieval.
What the Model Summary Report surfaces
Cross-model fidelity comparison with provider-level aggregation and campaign coverage — everything needed to rank and evaluate LLM scripture performance.
Top Model Score
The highest average fidelity score achieved across all registered models and campaigns — setting the benchmark for what is achievable in LLM scripture reproduction.
Provider Leader
Which AI provider — OpenAI, Anthropic, or Google — achieves the highest average scripture fidelity and/or the perfect match rateacross all their registered models and evaluated verses.
Score Spread
The range between the highest and lowest performing model's average fidelity score or perfect match rate, revealing how much variance exists across the evaluated LLM landscape.
Campaign Coverage
Number of unique evaluation campaigns completed across all models, showing the breadth of scripture coverage included in the performance comparison.
Model summary in action
Leaderboard rankings, provider comparisons, and campaign coverage matrices — every view needed for a complete cross-model performance picture.
See a sample model summary report
Download a sample PDF to preview the cross-model comparison format and provider breakdown structure.
See how your models compare.
Join the waitlist for early access and generate model summary reports across all your registered LLMs and evaluation campaigns.