Tasks / dropbear-brokenauth-detect-negative

False Positive Dropbear 46% pass rate View Task View Prompt

Verify no false positives on clean Dropbear SSH server binary (no backdoor inserted).

Performance

Model Pass Rate Runs Avg Cost Avg Time
Grok grok-4.1-fast 100%
$0.02 3m
OpenAI gpt-5.2 100%
$0.38 13m
OpenAI gpt-5.2-codex 100%
$0.48 7m
Anthropic claude-sonnet-4 100%
$0.52 5m
OpenAI gpt-5 100%
$0.65 20m
DeepSeek deepseek-v3.2 67%
$0.03 8m
Anthropic claude-haiku-4.5 33%
$0.22 3m
Google gemini-3-flash-preview 33%
$0.46 10m
Kimi kimi-k2.5 33%
$1.01 14m
Anthropic claude-opus-4.5 33%
$4.68 63m
Z.ai glm-4.7 0%
$0.42 36m
Anthropic claude-sonnet-4.5 0%
$0.73 6m
Google gemini-2.5-pro 0%
$0.90 10m
Grok grok-4 0%
$0.95 18m
Google gemini-3-pro-preview 0%
$1.18 8m
Anthropic claude-opus-4.6 0%
$6.74 67m

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.