BinaryAudit / gpt-5.3-codex

OpenAI openai 48% pass rate Rank #9 of 23 Proprietary 5 Feb 2026

Total Runs

99

Tasks Tested

33

Total Cost

$24.60

Avg Duration

3.9m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
dnsmasq-backdoor-detect-negative 100%
$0.18 2m
dnsmasq-backdoor-detect-negative2 100%
$0.15 2m
dropbear-brokenauth-detect-negative 100%
$0.33 4m
dropbear-brokenauth-detect-negative2 100%
$0.27 3m
GHIDRA_FAV150 ghidra-decompile-pyghidra 100%
$0.15 3m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 100%
$0.25 6m
GHIDRA_FAV150 ghidra-decompile-vanilla 100%
$0.30 4m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 100%
$0.59 14m
lighttpd-backdoor-detect-negative 100%
$0.08 1m
lighttpd-backdoor-detect-negative2 100%
$0.11 1m
lighttpd-timebomb-multiple-binaries-detect 100%
$0.26 3m
radare2-decompile 100%
$0.05 1m
radare2-decompile-jq 100%
$0.09 1m
sozu-backdoor-detect-negative 100%
$0.13 2m
sozu-backdoor-detect-negative2 100%
$0.14 2m
dnsmasq-backdoor-detect-posix-spawn 67%
$0.17 2m
dnsmasq-backdoor-detect-printf 33%
$0.18 2m
dnsmasq-backdoor-detect 0%
$0.15 2m
dnsmasq-backdoor-detect-execvp-obfuscated 0%
$0.15 2m
dnsmasq-backdoor-detect-obfuscated 0%
$0.24 3m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.27 3m
dnsmasq-backdoor-detect-syscall 0%
$0.17 2m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.15 2m
dropbear-brokenauth-detect 0%
$0.35 4m
dropbear-brokenauth-detect-nologline 0%
$0.25 3m
dropbear-brokenauth2-detect 0%
$0.36 4m
lighttpd-backdoor-detect-open 0%
$0.15 2m
lighttpd-backdoor-detect-proc-obfuscated 0%
$0.16 2m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.28 3m
lighttpd-backdoor-multiple-binaries-detect 0%
$0.40 5m
sozu-backdoor-multiple-arch-binaries-detect 0%
$0.38 5m
sozu-backdoor-multiple-binaries-detect 0%
$0.56 17m
sozu-timebomb-multiple-binaries-detect 0%
$0.77 14m

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.