JarvisBench - User Interaction: leaderboard

Metric: User-interaction score (0-100), the mean grade of the answers to the fixed General question and one generated Follow-up question at an early and a late checkpoint of 30 causally replayed worker trajectories (20 single-agent, 10 multi-agent); each answer graded 0, 1 or 2 for grounded, direct and useful content by GPT-5.6-Luna and rescaled, failed answers counting as zero. Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1GPT-5.6 Sol (Non-reasoning)96.3
2Claude Opus 4.890.8
3DeepSeek V4 Pro (Non-reasoning)85.8
4GPT-OSS-120B84.6

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