Expert-SWE (OpenAI)

GPT-6 Cyber 83% leads since November 2026

Fading

Agents do long-horizon coding tasks with a median estimated human completion time of 20 hours.

OpenAI calls it an internal frontier eval. The GPT-5.5 post (April 23rd, 2026) reports 73.1% for GPT-5.5 and 68.5% for GPT-5.4.

Made by: OpenAI
Released: April 2026
Kind: Building whole projects
Level: Expert
Scored: Checked automatically
Answers: Agent task
Tasks: Kept private

Strongest model tested: GPT-5.5 #20 on the capability index
Last in a launch post: November 2026, dropped before it saturated
Last model added: November 2026

openai.com

Models scored in lab cards

Launch posts list it, from 1 lab

System card reports it, from 1 lab

GPT-6 Cyber leads with 83%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

1 GPT-6 Cyber 83%
2 GPT-5.5 73.1%

Source: Labs’ model cards

#	Model	Score	Setting	Date	Source
1	GPT-6 Cyber	83%		Nov 2026	Lab model card
2	GPT-5.5	73.1%		Apr 2026	Lab model card

2 models have held number one in labs’ own numbers since its release in April 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI

Lab claims 2 leaders

GPT-6 Cyber 83%

Source: Labs’ model cards

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far

Source: Labs’ model cards

Labs headline it less often now, last in November 2026

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

OpenAI

Date	Launch post	Score	As the post writes it
Nov 5, 2026	GPT-6 Cyber	83	ExpertSWE, long-horizon software-engineering tasks
Apr 23, 2026	GPT-5.5	73.1	Expert-SWE (Internal)

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
Nov 5, 2026	GPT-6 Cyber system card	83	ExpertSWE, long-horizon software-engineering tasks	AI R&D risk

GPT-6 Cyber leads with 83%

2 models have held number one in labs’ own numbers since its release in April 2026

Scores over time

Labs headline it less often now, last in November 2026

One system card reports it

More in Coding