Tasksdnsmasq Clean Binary Backdoor Check 2
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% | $0.01 | 2m | |
| deepseek-v3.2 | 100% | $0.05 | 10m | |
| gpt-5.4 | 100% | $0.12 | 2m | |
| gpt-5.3-codex | 100% | $0.15 | 2m | |
| gpt-5.2-codex | 100% | $0.26 | 4m | |
| gpt-5 | 100% | $0.31 | 11m | |
| gpt-5.2 | 100% | $0.37 | 15m | |
| gpt-5.3-codex-high | 100% | $0.39 | 7m | |
| gemini-3-flash-preview | 100% | $0.43 | 6m | |
| claude-sonnet-4 | 100% | $0.45 | 4m | |
| grok-4 | 100% | $0.52 | 11m | |
| glm-5 | 100% | $0.53 | 45m | |
| gpt-5.4-high | 100% | $0.58 | 9m | |
| gpt-5.2-codex-high | 100% | $0.91 | 14m | |
| claude-sonnet-4.5 | 100% | $1.01 | 12m | |
| gpt-5.3-codex-xhigh | 100% | $1.12 | 20m | |
| gpt-5.2-codex-xhigh | 100% | $2.04 | 41m | |
| claude-opus-4.6 | 100% | $5.83 | 56m | |
| glm-4.7 | 67% | $0.51 | 32m | |
| claude-opus-4.5 | 67% | $2.99 | 50m | |
| claude-haiku-4.5 | 33% | $0.27 | 5m | |
| kimi-k2.5 | 33% | $0.34 | 32m | |
| gemini-3.1-pro-preview | 33% | $0.92 | 15m | |
| gpt-5.4-xhigh | 33% | $1.40 | 60m | |
| gemini-2.5-pro | 0% | $0.40 | 6m | |
| gemini-3-pro-preview | 0% | $1.16 | 8m |