BinaryAudit / grok-4

Grok x ai 29% pass rate Rank #15 of 16 Proprietary 9 Jul 2025

Total Runs

98

Tasks Tested

33

Total Cost

$55.18

Avg Duration

13.0m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
dnsmasq-backdoor-detect-negative 100%
$0.62 13m
dnsmasq-backdoor-detect-negative2 100%
$0.52 11m
GHIDRA_FAV150 ghidra-decompile-vanilla 100%
$0.44 12m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 100%
$0.60 17m
sozu-backdoor-detect-negative2 100%
$0.22 5m
GHIDRA_FAV150 ghidra-decompile-pyghidra 67%
$0.32 11m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 67%
$0.74 23m
sozu-backdoor-detect-negative 67%
$0.21 6m
sozu-backdoor-multiple-arch-binaries-detect 67%
$0.39 11m
dnsmasq-backdoor-detect-posix-spawn 33%
$0.59 12m
dnsmasq-backdoor-detect-syscall 33%
$0.43 9m
dropbear-brokenauth-detect-negative2 33%
$0.63 14m
lighttpd-backdoor-detect-negative2 33%
$0.40 7m
radare2-decompile-jq 33%
$0.24 5m
sozu-backdoor-multiple-binaries-detect 33%
$0.60 18m
dnsmasq-backdoor-detect 0%
$0.36 7m
dnsmasq-backdoor-detect-execvp-obfuscated 0%
$0.44 9m
dnsmasq-backdoor-detect-obfuscated 0%
$0.44 8m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.75 16m
dnsmasq-backdoor-detect-printf 0%
$0.58 12m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.51 12m
dropbear-brokenauth-detect 0%
$0.46 10m
dropbear-brokenauth-detect-negative 0%
$0.95 18m
dropbear-brokenauth-detect-nologline 0%
$0.57 12m
dropbear-brokenauth2-detect 0%
$0.29 7m
lighttpd-backdoor-detect-negative 0%
$0.20 4m
lighttpd-backdoor-detect-open 0%
$0.49 10m
lighttpd-backdoor-detect-proc-obfuscated 0%
$0.65 11m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.00 <1m
lighttpd-backdoor-multiple-binaries-detect 0%
$1.09 21m
lighttpd-timebomb-multiple-binaries-detect 0%
$2.22 46m
radare2-decompile 0%
$0.36 11m
sozu-timebomb-multiple-binaries-detect 0%
$1.15 36m

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.