Verify no false positives on clean Sozu load balancer binary (no backdoor inserted).
Performance
| Model | Pass Rate | Runs | Avg Cost | Avg Time |
|---|---|---|---|---|
| deepseek-v3.2 | 100% | | $0.02 | 7m |
| claude-haiku-4.5 | 100% | | $0.06 | 1m |
| gpt-5 | 100% | | $0.09 | 3m |
| kimi-k2.5 | 100% | | $0.10 | 8m |
| gemini-2.5-pro | 100% | | $0.11 | 1m |
| gemini-3-flash-preview | 100% | | $0.11 | 4m |
| gpt-5.3-codex | 100% | | $0.13 | 2m |
| gpt-5.2-codex | 100% | | $0.14 | 2m |
| gpt-5.3-codex-high | 100% | | $0.15 | 3m |
| glm-4.7 | 100% | | $0.15 | 26m |
| claude-sonnet-4 | 100% | | $0.22 | 3m |
| claude-sonnet-4.5 | 100% | | $0.29 | 4m |
| gemini-3.1-pro-preview | 100% | | $0.36 | 6m |
| gpt-5.2 | 100% | | $0.41 | 11m |
| gpt-5.3-codex-xhigh | 100% | | $0.49 | 9m |
| gemini-3-pro-preview | 100% | | $0.62 | 6m |
| gpt-5.2-codex-xhigh | 100% | | $0.79 | 16m |
| gpt-5.2-codex-high | 100% | | $1.29 | 25m |
| claude-opus-4.5 | 100% | | $1.56 | 16m |
| claude-opus-4.6 | 100% | | $3.31 | 45m |
| glm-5 | 67% | | $0.19 | 18m |
| grok-4 | 67% | | $0.21 | 6m |
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.