Dynamic adversarial user simulationsBrowse 296

Dynamic adversarial user simulations

Does the model follow the publisher's safety policy under challenging prompts?

Version not specifiedExact reported variant
Safety4 ranked models6 reported values1 reportsHigher is better

Top rankings

One row per model, using its best reported score across effort settings.

4
RankModelBest scoreBest reported setting
1GPT-5.5OpenAI0.989Reported configurationOpenAI report3 values · 1 reportAug 6, 2026 · source
2GPT-5.3 InstantOpenAI0.987Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source
3GPT-5.6 LunaOpenAI0.965Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source
4GPT-5.6 SolOpenAI0.961Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source

Effort curve

Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.

0
No cost-linked effort sweep for this version.
Definition and comparison boundarylimited methodology

Does the model follow the publisher's safety policy under challenging prompts?

Publisher-defined safety behavior, robustness, or preparedness evaluations under the stated test protocol. Higher is better. Raw not_unsafe share in the publisher's [0,1] scale.

Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.

Dynamic multi-turn evaluation; metric is the share of assistant messages that do not violate safety policies.

Method / source