# Anthropic Binary Exploitation Benchmark (formerly OSS-Fuzz), control-flow hijacks (Binary Exploitation Benchmark)

> Anthropic's unguided vulnerability-discovery and exploitation evaluation: from a single function entry point in an open-source project, the model must find a bug and push it toward a working exploit. This lane counts control-flow hijacks.

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

- Category: [Agentic](/agentic)
- Last updated: November 11, 2026

## About Binary Exploitation Benchmark

- Year: 2026
- Tasks: Open-source function entry points
- Format: Count of control-flow hijacks
- Difficulty: Exploit development
- Paper: [Claude Fable 5.2 and Claude Mythos 5.2 system card](https://assets.claude.com/27d60918d218125e7504bc7354c4b4626ec56b11.pdf)

Run with cyber mitigations off. Earlier system cards reported this evaluation as OSS-Fuzz crash and write-primitive rates, stored on separate lanes; the Fable 5.2 card reports counts of control-flow hijacks. Dual-use offensive capability, so display-only.

Binary Exploitation Benchmark is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (4 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Mythos 5.2](/models/claude-mythos-5-2) | Anthropic | 148 |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | 112 |
| 3 | [Claude Mythos 5.1](/models/claude-mythos-5-1) | Anthropic | 84 |
| 4 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | 48 |

## FAQ

### What does Binary Exploitation Benchmark measure?

Anthropic's unguided vulnerability-discovery and exploitation evaluation: from a single function entry point in an open-source project, the model must find a bug and push it toward a working exploit. This lane counts control-flow hijacks.

### Which model scores highest on Binary Exploitation Benchmark?

Claude Mythos 5.2 by Anthropic currently leads with a score of 148 on Binary Exploitation Benchmark.

### How many models are evaluated on Binary Exploitation Benchmark?

4 AI models have published results on Binary Exploitation Benchmark in the BenchLM catalog.

### Does Binary Exploitation Benchmark affect BenchLM's overall score?

Not directly. Binary Exploitation Benchmark is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on Binary Exploitation Benchmark

- [Claude Mythos 5.2 vs Claude Opus 5.5](/compare/claude-mythos-5-2-vs-claude-opus-5-5)
- [Claude Opus 5.5 vs Claude Mythos 5.1](/compare/claude-mythos-5-1-vs-claude-opus-5-5)
- [Claude Mythos 5.1 vs Claude Sonnet 5.5](/compare/claude-mythos-5-1-vs-claude-sonnet-5-5)