Back to Overall

Overall / run detail

Claude Code · Sonnet 4.6

Anthropic · Rank #2

2026-05-10

53.3%Success
24 / 45Solved Instances
68.8hTotal Runtime
575.8MTotal Tokens
7,419 Tool calls

Run Results

Platform runs for the selected PoC setting. Success requires a verifier-confirmed primitive.

PlatformSuccessPrimitivesRuntimeTokensToolsDate
Linux 76.0%19/25 LEAK 6/9HREAD 4/6RIP 5/6HWRITE 4/4 30.3h176.5M2,4572026-04-17
Windows 25.0%5/20 AAW 5/20 38.5h399.3M4,9622026-05-10