RankingComputer-use safety stress test · Sol 6.1 launch / safety stress test

Computer-use safety stress test · Sol 6.1 launch / safety stress test

Data updated 29 Sept 2026

Bucket: Supporting evidence
Unit: percent
Direction: Lower is better
Version: Sol 6.1 launch / safety stress test
Display harness: Introducing GPT-6.1 Sol
Board: https://openai.com/index/introducing-gpt-6-1-sol/

The available records have no admitted matched comparison in the capability core. Raw results remain available below.

Compare published benchmark results with category weights →

Models

Published configurations retain their source and harness labels. Missing results remain unknown.

1–4 of 4 entries

Model	Score	Harness	Evidence	Source-recorded date
GPT-6 AstraOpenAI	2.4% Reported settings & source Reported reasoning effort xhigh. Unintended outcomes in deliberately adversarial computer- and browser-use workplace tasks; the updated harder safety subset, not OSWorld task success. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Computer-use safety stress test (lower is better) / GPT-6 Astra / xhigh · reviewed 2026-09-29	Introducing GPT-6.1 Sol	lab self-report	2026-09-29
GPT-6.1 SolOpenAI	4.32% Reported settings & source Reported reasoning effort xhigh. Unintended outcomes in deliberately adversarial computer- and browser-use workplace tasks; the updated harder safety subset, not OSWorld task success. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Computer-use safety stress test (lower is better) / GPT-6.1 Sol / xhigh · reviewed 2026-09-29	Introducing GPT-6.1 Sol	lab self-report	2026-09-29
GPT-6 LunaOpenAI	13.7% Reported settings & source Reported reasoning effort xhigh. Unintended outcomes in deliberately adversarial computer- and browser-use workplace tasks; the updated harder safety subset, not OSWorld task success. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Computer-use safety stress test (lower is better) / GPT-6 Luna / xhigh · reviewed 2026-09-29	Introducing GPT-6.1 Sol	lab self-report	2026-09-29
GPT-6 SolOpenAI	17.39% Reported settings & source Reported reasoning effort xhigh. Unintended outcomes in deliberately adversarial computer- and browser-use workplace tasks; the updated harder safety subset, not OSWorld task success. OpenAI research environment or API; same named metric and evaluation chart. No fallback is reported for this OpenAI configuration. Provider-published lab self-report. Safety stress outcomes are retained for inspection and excluded from capability scoring. Competitor results are republished from public reports; the page does not establish independent reproduction by OpenAI. Comparison limit: Safety failure behavior is not a capability or intelligence score. Introducing GPT-6.1 Sol · Chart: Computer-use safety stress test (lower is better) / GPT-6 Sol / xhigh · reviewed 2026-09-29	Introducing GPT-6.1 Sol	lab self-report	2026-09-29