# ExploitBench Internal Port 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://modelscale.dev/leaderboards/benchmarks/external-exploit-bench-internal-port

ExploitBench — Internal Port (June–August 2026). Every model the catalog carries a published ExploitBench Internal Port value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Mean arbitrary-code-execution success rate |
| Tasks | Recently disclosed V8 and Chrome vulnerabilities (June–August 2026) |
| Difficulty | Browser exploitation |
| Published by | [GPT-6 Cyber System Card](https://deploymentsafety.openai.com/gpt-6-cyber) |

OpenAI's internal port of ExploitBench restricted to V8 and Chrome vulnerabilities disclosed in June to August 2026, to limit contamination from historical exploits.

## ExploitBench Internal Port ranking

9 models with a published ExploitBench Internal Port 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 | Mean arbitrary-code-execution success rate | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6.2 Astra](https://modelscale.dev/models/gpt-6-2-astra) | OpenAI | 53.5 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6.2 Sol](https://modelscale.dev/models/gpt-6-2-sol) | OpenAI | 50.5 | Observed 2026-11-21 · source benchlm:models |
| 3 | [GPT-6 Cyber](https://modelscale.dev/models/gpt-6-cyber) | OpenAI | 42.0 | Observed 2026-11-21 · source benchlm:models |
| 4 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 39.0 | Observed 2026-11-21 · source benchlm:models |
| 5 | [GPT-6.1 Terra](https://modelscale.dev/models/gpt-6-1-terra) | OpenAI | 24.5 | Observed 2026-11-21 · source benchlm:models |
| 6 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 21.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-5.6 Sol](https://modelscale.dev/models/gpt-5-6-sol) | OpenAI | 5.5 | Observed 2026-11-21 · source benchlm:models |
| 7 | [GPT-6 Sol](https://modelscale.dev/models/gpt-6-sol) | OpenAI | 5.5 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-6 Luna](https://modelscale.dev/models/gpt-6-luna) | OpenAI | 0.0 | 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.
