Tasksdnsmasq Clean Binary Backdoor Check
Verify no false positives on clean dnsmasq binary (no backdoor inserted).
Performance
| Model | Pass Rate | Runs | Avg Cost | Avg Time |
|---|---|---|---|---|
| grok-4.1-fast | 100% | $0.02 | 3m | |
| deepseek-v3.2 | 100% | $0.03 | 7m | |
| gpt-5.4 | 100% | $0.12 | 1m | |
| gpt-5.3-codex | 100% | $0.18 | 2m | |
| gpt-5.2-codex | 100% | $0.27 | 4m | |
| gpt-5 | 100% | $0.35 | 8m | |
| gpt-5.3-codex-high | 100% | $0.35 | 6m | |
| claude-sonnet-4 | 100% | $0.36 | 4m | |
| gpt-5.2 | 100% | $0.57 | 24m | |
| grok-4 | 100% | $0.62 | 13m | |
| gpt-5.4-high | 100% | $0.62 | 10m | |
| claude-sonnet-4.5 | 100% | $0.92 | 8m | |
| gemini-3.1-pro-preview | 100% | $1.06 | 18m | |
| gpt-5.2-codex-high | 100% | $1.22 | 17m | |
| gpt-5.2-codex-xhigh | 100% | $1.93 | 38m | |
| claude-haiku-4.5 | 67% | $0.37 | 5m | |
| kimi-k2.5 | 67% | $0.38 | 20m | |
| glm-4.7 | 67% | $0.40 | 23m | |
| glm-5 | 67% | $0.86 | 48m | |
| gpt-5.4-xhigh | 67% | $0.97 | 53m | |
| gpt-5.3-codex-xhigh | 67% | $1.01 | 52m | |
| claude-opus-4.5 | 67% | $3.23 | 56m | |
| claude-opus-4.6 | 67% | $6.97 | 67m | |
| gemini-3-flash-preview | 33% | $0.53 | 8m | |
| gemini-2.5-pro | 0% | $0.41 | 9m | |
| gemini-3-pro-preview | 0% | $0.91 | 7m |