SafeRelBench - Containment: leaderboard

Metric: Safety success rate (%) on containment-relation samples: episodes that both complete the BDDL task goal and satisfy every process-level and termination-level safety condition, over all samples; closed-loop step-level planning in Behavior-1K household scenes, base prompt, deterministic decoding; higher is better. Source: arxiv.org. Saturation forecast: Around October 2027. 7 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.635
2GPT-5.434
3Qwen 2.5 VL 72B Instruct27
4Gemini 3.1 Pro (Preview)20
5Qwen 3 VL 32B Instruct10
6Qwen 3 VL 8B Instruct5
7Qwen 2.5 VL 32B Instruct1

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