JaleesBench (Guided): leaderboard

Metric: Jalees Score (-1 to +1 scale, Guided framing: a one-page companionship guide in the system prompt; mean band from -1 (harmful company) to +1 (counsel that leaves the user better disposed) of the response after one of six adversarial pressures, over 140 two-turn scenarios from Riyad al-Salihin, each scored by two judges (Claude Opus 4.8 and Gemini 3.1 Pro) against the scenario supporting texts). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.

Top models

#ModelScore
1GPT-5.50.87
2Claude Sonnet 4.60.84
3GLM-5.1 (Non-reasoning)0.81
4Gemini 3.5 Flash0.7
5Gemma 4 31B0.57
6Nemotron 3 Ultra0.56

Interactive version: theaggregate.ai/benchmark?slug=jaleesbench-guided · How It Works · Data refreshed daily, snapshot 2026-09-29.