# Refusal of harmful cyber requests (JailbreakBench, StrongREJECT, AgentHarm) (Cyber Misuse Refusal)

> Average refusal rate on the cyber-related prompts of JailbreakBench, StrongREJECT and AgentHarm, as measured by Mistral. Higher means the model refuses more malicious cyber requests.

Canonical page: https://benchlm.ai/benchmarks/cyberharmfulrefusal

- Category: [Agentic](/agentic)
- Last updated: October 29, 2026

## About Cyber Misuse Refusal

- Year: 2026
- Tasks: Cyber-related harmful prompts from three safety benchmarks
- Format: Average refusal rate
- Difficulty: Cyber misuse safety
- Paper: [Mistral Large 4 is now open weight](https://mistral.ai/news/mistral-large-4-oss/)

Mistral reported these results in its October 29, 2026 Mistral Large 4 open-weight post, including the rival-model values in its chart. They are provider-run, so BenchLM shows them display-only and keeps them out of weighted scores. This is Mistral's own composite, not a public leaderboard; rival values were published as whole percentages.

Cyber Misuse Refusal is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (4 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Mistral Large 4](/models/mistral-large-4) | Mistral | 96.6% |
| 2 | [Kimi K3](/models/kimi-k3) | Moonshot AI | 94.0% |
| 3 | [GLM-5.3](/models/glm-5-3) | Z.AI | 87.0% |
| 4 | [Gemma 4 31B](/models/gemma-4-31b) | Google | 84.0% |

## FAQ

### What does Cyber Misuse Refusal measure?

Average refusal rate on the cyber-related prompts of JailbreakBench, StrongREJECT and AgentHarm, as measured by Mistral. Higher means the model refuses more malicious cyber requests.

### Which model scores highest on Cyber Misuse Refusal?

Mistral Large 4 by Mistral currently leads with a score of 96.6% on Cyber Misuse Refusal.

### How many models are evaluated on Cyber Misuse Refusal?

4 AI models have published results on Cyber Misuse Refusal in the BenchLM catalog.

### Does Cyber Misuse Refusal affect BenchLM's overall score?

Not directly. Cyber Misuse Refusal is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on Cyber Misuse Refusal

- [Mistral Large 4 vs Kimi K3](/compare/kimi-k3-vs-mistral-large-4)
- [Kimi K3 vs GLM-5.3](/compare/glm-5-3-vs-kimi-k3)
- [GLM-5.3 vs Gemma 4 31B](/compare/gemma-4-31b-vs-glm-5-3)