SCONE Post-Cutoff Exploit Success (SCONE post-cutoff success)
Share of SCONE smart-contract vulnerabilities exploited on the 12-task post-cutoff set.
Benchmark score on SCONE post-cutoff success — August 13, 2026
BenchLM mirrors the published score view for SCONE post-cutoff success. Claude Mythos Preview leads the public snapshot at 100%. We do not use these results to rank models overall.
Benchmark score table (1 model)
ScoreAbout SCONE post-cutoff success
Year
2026
Tasks
12 post-cutoff smart-contract vulnerabilities
Format
Best@8 exploit success rate
Difficulty
Smart-contract exploitation
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.
BenchLM freshness & provenance
Version
SCONE post-cutoff success 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
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.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.