benchmaxxer Sep 23, 2026
Production BenchmarksBrowse 296

Production Benchmarks

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-5.3 InstantOpenAI0.943Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source
2GPT-5.5OpenAI0.943Reported configurationOpenAI report3 values · 1 reportAug 6, 2026 · source
3GPT-5.6 LunaOpenAI0.925Reported configurationOpenAI report1 value · 1 reportAug 6, 2026 · source
4GPT-5.6 SolOpenAI0.906Reported 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.

Production Benchmarks with Challenging Prompts; evaluations run without system-level safeguards on difficult production-derived examples.

Method / source