BinaryAudit / gpt-5.2-codex-high

OpenAI openai 61% pass rate Rank #5 of 23 Proprietary 18 Dec 2025

Total Runs

98

Tasks Tested

33

Total Cost

$108.96

Avg Duration

15.5m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
dnsmasq-backdoor-detect 100%
$0.83 12m
dnsmasq-backdoor-detect-negative 100%
$1.22 17m
dnsmasq-backdoor-detect-negative2 100%
$0.91 14m
dnsmasq-backdoor-detect-obfuscated 100%
$1.25 17m
dnsmasq-backdoor-detect-posix-spawn 100%
$0.69 9m
dropbear-brokenauth-detect-negative 100%
$1.31 16m
dropbear-brokenauth-detect-negative2 100%
$1.39 17m
GHIDRA_FAV150 ghidra-decompile-pyghidra 100%
$0.26 6m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 100%
$0.30 6m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 100%
$0.90 15m
lighttpd-backdoor-detect-negative 100%
$0.50 7m
lighttpd-backdoor-detect-negative2 100%
$0.54 7m
radare2-decompile 100%
$0.21 3m
radare2-decompile-jq 100%
$0.12 2m
sozu-backdoor-detect-negative 100%
$1.29 25m
sozu-backdoor-detect-negative2 100%
$0.53 7m
dnsmasq-backdoor-detect-execvp-obfuscated 67%
$0.82 11m
dnsmasq-backdoor-detect-printf 67%
$1.01 15m
dnsmasq-backdoor-detect-syscall 67%
$0.94 14m
GHIDRA_FAV150 ghidra-decompile-vanilla 67%
$0.48 7m
lighttpd-backdoor-multiple-binaries-detect 67%
$1.24 15m
lighttpd-timebomb-multiple-binaries-detect 67%
$1.16 15m
sozu-backdoor-multiple-binaries-detect 33%
$2.39 34m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.86 11m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.91 13m
dropbear-brokenauth-detect 0%
$1.44 17m
dropbear-brokenauth-detect-nologline 0%
$1.65 22m
dropbear-brokenauth2-detect 0%
$1.56 20m
lighttpd-backdoor-detect-open 0%
$1.63 24m
lighttpd-backdoor-detect-proc-obfuscated 0%
$1.21 18m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.63 8m
sozu-backdoor-multiple-arch-binaries-detect 0%
$3.45 46m
sozu-timebomb-multiple-binaries-detect 0%
$2.86 40m

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.