DTap-Bench (Benign Tasks) - Legal: leaderboard

Metric: Benign task success rate (%; 200 benign legal practice tasks, no attack applied; a task succeeds when a rule-based check of the final environment state finds the instruction fully completed; mean of its task-category rates). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.

Top models

#ModelScore
1GPT-5.490.5
2GPT-5.187.2
3Gemini 3 Pro87.1
4GPT-5.285.7
5GPT-OSS-120B9.7

Interactive version: theaggregate.ai/benchmark?slug=dtap-bench-benign-tasks-legal · How It Works · Data refreshed daily, snapshot 2026-09-26.