DTap-Bench (Benign Tasks) - Research: leaderboard
Metric: Benign task success rate (%; 160 benign research 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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 100 |
| 2 | GPT-5.4 | 95 |
| 3 | GPT-5.2 | 94.5 |
| 4 | GPT-5.1 | 90 |
| 5 | GPT-OSS-120B | 30 |
Interactive version: theaggregate.ai/benchmark?slug=dtap-bench-benign-tasks-research · How It Works · Data refreshed daily, snapshot 2026-09-26.