# The Last Ones completion 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-last-ones-cyber-range-completion

The Last Ones Cyber Range Completion Rate. Every model the catalog carries a published The Last Ones completion value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Completion rate |
| Tasks | 10 long-horizon runs |
| Difficulty | Long-horizon cyber operations |
| Published by | [UK AISI and CAISI Preliminary Assessment of Kimi K3's Cyber Capabilities](https://www.nist.gov/news-events/news/2026/07/uk-aisi-caisi-preliminary-assessment-kimi-k3s-cyber-capabilities) |

Share of runs that completed the 32-step cyber range within the 100-million-token limit.

## The Last Ones completion ranking

3 models with a published The Last Ones completion 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-5.6 Sol](https://modelchoice.dev/models/gpt-5-6-sol) | OpenAI | 70 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Claude Mythos 5](https://modelchoice.dev/models/claude-mythos-5) | Anthropic | 60 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Kimi K3](https://modelchoice.dev/models/kimi-3) | Moonshot AI | 10 | 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.
