# StrongREJECT 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-strong-reject-none

StrongREJECT (no jailbreak). Every model the catalog carries a published StrongREJECT value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Safe-response score (%) |
| Tasks | Forbidden requests across harm categories |
| Difficulty | Harmful-request refusal |
| Published by | [A StrongREJECT for Empty Jailbreaks](https://arxiv.org/abs/2402.10260) |

StrongREJECT scores how well a model refuses forbidden requests; this setting sends the harmful prompts without any jailbreak wrapper. Higher scores mean safer responses.

## StrongREJECT ranking

2 models with a published StrongREJECT 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 | Safe-response score (%) | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Inkling 2 Mini](https://modelscale.dev/models/inkling-2-mini) | Thinking Machines Lab | 97.8 | Observed 2026-11-21 · source benchlm:models |
| 1 | [Inkling 2 Small](https://modelscale.dev/models/inkling-2-small) | Thinking Machines Lab | 97.8 | 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.
