OpenAI

GPT-5.5 Instant

• System card dated 4 May 2026
• Framework: Preparedness Framework
• 4 statements about capability levels
• 13 tests by the provider
• 1 source document

What the provider states

• Autonomy & replication · Below high capability · Stated as not crossed

  gpt-5.5 instant is considered below high capability.

  OpenAI · 4 May 2026 · Read the source
• Autonomy & replication · High · Stated as not crossed

  for ai self-improvement, evaluations of final checkpoints indicate that, like its predecessor models, gpt-5.5 instant does not have a plausible chance of reaching a high threshold.

  OpenAI · 4 May 2026 · Read the source
• Chemical, biological, radiological and nuclear · High · Stated as crossed

  gpt-5.5 instant is our first instant model to be treated as high capability in the biological and chemical domain, as well as in the cybersecurity domain.

  OpenAI · 4 May 2026 · Read the source
• Cyber · High · Stated as crossed

  this is the first instant model that we are treating as high capability in our cybersecurity and biological & chemical preparedness categories, and implementing appropriate safeguards.

  OpenAI · 4 May 2026 · Read the source
  The same level is stated in 1 other sentence, counted once. Show it.

  because of this, we similarly treat gpt-5.5 instant as high under the preparedness framework.

  OpenAI · 4 May 2026 · Read the source

The provider's own tests

• CVE-Bench · The provider · Cyber

  gpt-5.5 instant performs higher than gpt-5.4 thinking and lower than gpt-5.5 thinking.

  OpenAI · 4 May 2026 · Read the source
• Cyber Range · The provider · Cyber

  however, gpt-5.5 instant is significantly less capable than gpt-5.5 thinking in cybersecurity, due to its poor performance on long-horizon tasks, and as evidenced by lower performance on ctf, cve-bench, and significantly lower performance on cyber range.

  OpenAI · 4 May 2026 · Read the source
• TroubleshootingBench · The provider · Chemical, biological, radiological and nuclear

  gpt-5.5 instant performs below the comparison models, and below the expert baseline of 36.4%.

  OpenAI · 4 May 2026 · Read the source
• azure ssrf · The provider · Cyber

  azure ssrf exploit a vulnerable web application, steal valid credentials, and modify access control policies for lateral movement.

  OpenAI · 4 May 2026 · Read the source
• basic command and control (c2) · The provider · Cyber

  basic command and control (c2) discover allowed communication channels when establishing a new foothold.

  OpenAI · 4 May 2026 · Read the source
• coffee roasters · The provider · Cyber

  coffee roasters exploit a vulnerable web application and then pivot to an active directory environment, with some amount of distraction in the environment.

  OpenAI · 4 May 2026 · Read the source
• firewall evasion · The provider · Cyber

  firewall evasion the agent must use a known vulnerability in a network service to obtain privileged credentials and then use those credentials to pivot and modify network policy.

  OpenAI · 4 May 2026 · Read the source
• first-person fairness evaluation · The provider · Bias

  Reported result: gpt-5.5 instant scored 0.0101 on harm_overall.

  gpt-5.5 instant scored 0.0101 on this metric, broadly comparable to gpt-5.2-instant and gpt-5.3-instant.

  OpenAI · 4 May 2026 · Read the source
• https oracle · The provider · Cyber

  https oracle identify and exploit a cryptographic implementation vulnerability in a webserver by eavesdropping on traffic.

  OpenAI · 4 May 2026 · Read the source
• medium command and control (c2) · The provider · Cyber

  medium command and control (c2) expanded version of the basic c2 scenario: the agent must pivot to the target host through an intermediary with unstable c2, then perform privilege escalation on the end host.

  OpenAI · 4 May 2026 · Read the source

No document we read states: a release date, an independent or government test, a safeguard. No incident on record names this version.

Some documents we hold are stored in lower case only, so their quotes are shown in lower case. The source link opens the original.

Compare with other versions