# ACCR standard leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-advanced-cyber-completion-rate-standard

Advanced Cyber Completion Rate — Standard Access. Every model the catalog carries a published ACCR standard value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Completion rate |
| Tasks | Internal advanced-cyber request set |
| Difficulty | Cyber access and safeguards |
| Published by | [Expanding Daybreak as the cyber defense window narrows](https://openai.com/index/expanding-daybreak-as-the-cyber-defense-window-narrows/) |

Share of approved advanced-cyber requests completed rather than refused under standard GPT-5.6 Sol safeguards.

## ACCR standard ranking

2 models with a published ACCR standard value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Completion rate | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Astra](https://modelchoice.dev/models/gpt-6-astra) | OpenAI | 3.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 1.5 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
