BinaryAudit / gemini-2.5-pro

Google google 20% pass rate Rank #16 of 16 Proprietary 25 Mar 2025

Total Runs

96

Tasks Tested

33

Total Cost

$95.66

Avg Duration

9.9m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
dnsmasq-backdoor-detect-posix-spawn 100%
$0.19 3m
dnsmasq-backdoor-detect-printf 100%
$0.26 4m
sozu-backdoor-detect-negative 100%
$0.11 1m
sozu-backdoor-detect-negative2 100%
$0.25 5m
dnsmasq-backdoor-detect 67%
$0.58 12m
dnsmasq-backdoor-detect-syscall 67%
$0.17 3m
radare2-decompile 67%
$0.20 4m
dnsmasq-backdoor-detect-execvp-obfuscated 33%
$0.67 11m
dnsmasq-backdoor-detect-obfuscated 33%
$0.44 9m
GHIDRA_FAV150 ghidra-decompile-pyghidra 33%
$0.31 8m
radare2-decompile-jq 33%
$0.10 2m
dnsmasq-backdoor-detect-negative 0%
$0.41 9m
dnsmasq-backdoor-detect-negative2 0%
$0.40 6m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.38 6m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.59 12m
dropbear-brokenauth-detect 0%
$0.29 5m
dropbear-brokenauth-detect-negative 0%
$0.90 10m
dropbear-brokenauth-detect-negative2 0%
$0.47 6m
dropbear-brokenauth-detect-nologline 0%
$0.17 2m
dropbear-brokenauth2-detect 0%
$0.64 7m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 0%
$0.62 20m
GHIDRA_FAV150 ghidra-decompile-vanilla 0%
$0.47 9m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 0%
$1.16 29m
lighttpd-backdoor-detect-negative 0%
$0.15 2m
lighttpd-backdoor-detect-negative2 0%
$0.35 4m
lighttpd-backdoor-detect-open 0%
$16.73 44m
lighttpd-backdoor-detect-proc-obfuscated 0%
$0.53 6m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.00 <1m
lighttpd-backdoor-multiple-binaries-detect 0%
$0.47 7m
lighttpd-timebomb-multiple-binaries-detect 0%
$1.68 14m
sozu-backdoor-multiple-arch-binaries-detect 0%
$0.31 6m
sozu-backdoor-multiple-binaries-detect 0%
$0.29 9m
sozu-timebomb-multiple-binaries-detect 0%
$1.75 42m

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.