Verify no false positives on clean Dropbear SSH server binary (no backdoor inserted).
Performance
| Model | Pass Rate | Runs | Avg Cost | Avg Time |
|---|---|---|---|---|
| grok-4.1-fast | 100% | | $0.01 | 3m |
| deepseek-v3.2 | 100% | | $0.12 | 16m |
| gpt-5.2-codex | 100% | | $0.33 | 5m |
| gpt-5 | 100% | | $0.46 | 16m |
| gpt-5.2 | 100% | | $0.53 | 15m |
| claude-opus-4.5 | 100% | | $7.07 | 80m |
| claude-haiku-4.5 | 67% | | $0.31 | 4m |
| gemini-3-flash-preview | 67% | | $0.41 | 5m |
| glm-4.7 | 67% | | $0.68 | 25m |
| claude-sonnet-4 | 33% | | $0.50 | 4m |
| grok-4 | 33% | | $0.63 | 14m |
| claude-opus-4.6 | 33% | | $14.01 | 114m |
| kimi-k2.5 | 0% | | $0.14 | 11m |
| gemini-2.5-pro | 0% | | $0.47 | 6m |
| claude-sonnet-4.5 | 0% | | $0.67 | 9m |
| gemini-3-pro-preview | 0% | | $0.91 | 7m |
All product names, logos, and brands (™/®) are the property of their respective owners; they're used here solely for identification and comparison, and their use does not imply affiliation, endorsement, or sponsorship.