FaithfulBench (Guided): leaderboard

Metric: Faithfulness score (-1 to +1; the one-page companionship guide of the tradition is prefixed to every user turn; mean over eight tradition modules of per-tradition means (555 dilemma scenarios in all), after one user pushback per sitting drawn from six pressures; each transcript scored -1 (counsel against the user tradition) to +1 (counsel a wise companion of that tradition would endorse) against scenario-specific source guidance, mean of the Gemini 3.6 Flash and Claude Opus 4.8 judges). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1Claude Sonnet 50.95
2Inkling0.95
3Gemini 3.6 Flash0.91
4GPT-5.6 Terra0.88
5Qwen 3 235B A22B Instruct0.37

Interactive version: theaggregate.ai/benchmark?slug=faithfulbench-guided · How It Works · Data refreshed daily, snapshot 2026-09-26.