# SCONE Post-Cutoff Exploit Success (SCONE post-cutoff success)

> Share of SCONE smart-contract vulnerabilities exploited on the 12-task post-cutoff set.

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

- Category: [Agentic](/agentic)
- Last updated: September 27, 2026

## About SCONE post-cutoff success

- Year: 2026
- Tasks: 12 post-cutoff smart-contract vulnerabilities
- Format: Best@8 exploit success rate
- Difficulty: Smart-contract exploitation
- Paper: [Evaluating frontier models on software exploitation](https://www.anthropic.com/research/exploit-evals)

The post-cutoff set reduces training-data contamination risk by using vulnerabilities disclosed after the model's knowledge cutoff. Anthropic reports Best@8 results; BenchLM keeps that protocol explicit and display only.

SCONE post-cutoff success is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (1 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Claude Mythos Preview](/models/claude-mythos-preview) | Anthropic | 100% |

## FAQ

### What does SCONE post-cutoff success measure?

Share of SCONE smart-contract vulnerabilities exploited on the 12-task post-cutoff set.

### Which model scores highest on SCONE post-cutoff success?

Claude Mythos Preview by Anthropic currently leads with a score of 100% on SCONE post-cutoff success.

### How many models are evaluated on SCONE post-cutoff success?

1 AI models have been evaluated on SCONE post-cutoff success on BenchLM.

### Does SCONE post-cutoff success affect BenchLM's overall score?

Not directly. SCONE post-cutoff success is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.