# SCONE Post-Cutoff Simulated Exploit Revenue (SCONE simulated revenue)

> Simulated value captured across the SCONE post-cutoff smart-contract set.

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

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

## About SCONE simulated revenue

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

Anthropic reports the simulated on-chain value captured by successful exploits. This dollar-denominated metric describes the benchmark environment and must not be read as real-world revenue.

SCONE simulated revenue 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 | 35% |

## FAQ

### What does SCONE simulated revenue measure?

Simulated value captured across the SCONE post-cutoff smart-contract set.

### Which model scores highest on SCONE simulated revenue?

Claude Mythos Preview by Anthropic currently leads with a score of 35% on SCONE simulated revenue.

### How many models are evaluated on SCONE simulated revenue?

1 AI models have been evaluated on SCONE simulated revenue on BenchLM.

### Does SCONE simulated revenue affect BenchLM's overall score?

Not directly. SCONE simulated revenue is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.