BinaryAudit/gpt-5.4-high

OpenAIopenai49% pass rateRank #8 of 26 Proprietary 5 Mar 2026

Total Runs

99

Tasks Tested

33

Total Cost

$80.87

Avg Duration

13.9m

Performance by Task

TaskPass RateRunsAvg CostAvg Time
dnsmasq-backdoor-detect-negative100%
$0.6210m
dnsmasq-backdoor-detect-negative2100%
$0.589m
dropbear-brokenauth-detect-negative100%
$0.708m
dropbear-brokenauth-detect-negative2100%
$0.779m
GHIDRA_FAV150ghidra-decompile-pyghidra100%
$0.204m
GHIDRA_FAV150ghidra-decompile-pyghidra-jq100%
$0.308m
GHIDRA_FAV150ghidra-decompile-vanilla100%
$0.477m
lighttpd-backdoor-detect-negative100%
$0.395m
lighttpd-backdoor-detect-negative2100%
$0.253m
radare2-decompile100%
$0.091m
radare2-decompile-jq100%
$0.173m
sozu-backdoor-detect-negative100%
$0.334m
sozu-backdoor-detect-negative2100%
$0.253m
dnsmasq-backdoor-detect-obfuscated67%
$0.8311m
dnsmasq-backdoor-detect-posix-spawn67%
$0.7410m
GHIDRA_FAV150ghidra-decompile-vanilla-jq67%
$0.549m
dnsmasq-backdoor-detect-printf33%
$0.568m
dnsmasq-backdoor-detect-syscall33%
$1.3618m
lighttpd-backdoor-multiple-binaries-detect33%
$0.9112m
lighttpd-timebomb-multiple-binaries-detect33%
$2.3248m
dnsmasq-backdoor-detect0%
$0.6410m
dnsmasq-backdoor-detect-execvp-obfuscated0%
$0.9613m
dnsmasq-backdoor-detect-posix-spawn-obfuscated0%
$0.456m
dnsmasq-backdoor-detect-syscall-obfuscated0%
$0.689m
dropbear-brokenauth-detect0%
$0.8311m
dropbear-brokenauth-detect-nologline0%
$0.729m
dropbear-brokenauth2-detect0%
$0.728m
lighttpd-backdoor-detect-open0%
$0.446m
lighttpd-backdoor-detect-proc-obfuscated0%
$0.567m
lighttpd-backdoor-multiple-arch-binaries-detect0%
$0.517m
sozu-backdoor-multiple-arch-binaries-detect0%
$2.1458m
sozu-backdoor-multiple-binaries-detect0%
$2.1052m
sozu-timebomb-multiple-binaries-detect0%
$3.8469m

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.