BinaryAudit / claude-haiku-4.5

Anthropic anthropic 33% pass rate Rank #14 of 16 Proprietary 15 Oct 2025

Total Runs

99

Tasks Tested

33

Total Cost

$32.41

Avg Duration

7.4m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
radare2-decompile 100%
$0.09 4m
sozu-backdoor-detect-negative 100%
$0.06 1m
sozu-backdoor-detect-negative2 100%
$0.11 1m
dnsmasq-backdoor-detect 67%
$0.18 3m
dnsmasq-backdoor-detect-negative 67%
$0.37 5m
dropbear-brokenauth-detect-negative2 67%
$0.31 4m
GHIDRA_FAV150 ghidra-decompile-vanilla 67%
$0.15 5m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 67%
$0.30 23m
lighttpd-backdoor-detect-negative 67%
$0.18 2m
lighttpd-backdoor-detect-negative2 67%
$0.16 5m
radare2-decompile-jq 67%
$0.24 18m
sozu-backdoor-multiple-arch-binaries-detect 67%
$0.20 6m
dnsmasq-backdoor-detect-negative2 33%
$0.27 5m
dnsmasq-backdoor-detect-syscall 33%
$0.50 6m
dropbear-brokenauth-detect-negative 33%
$0.22 3m
dropbear-brokenauth-detect-nologline 33%
$0.39 5m
GHIDRA_FAV150 ghidra-decompile-pyghidra 33%
$0.38 15m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 33%
$0.38 22m
dnsmasq-backdoor-detect-execvp-obfuscated 0%
$0.29 5m
dnsmasq-backdoor-detect-obfuscated 0%
$0.28 4m
dnsmasq-backdoor-detect-posix-spawn 0%
$0.42 5m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.38 4m
dnsmasq-backdoor-detect-printf 0%
$0.38 5m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.41 6m
dropbear-brokenauth-detect 0%
$0.60 8m
dropbear-brokenauth2-detect 0%
$0.36 6m
lighttpd-backdoor-detect-open 0%
$0.46 5m
lighttpd-backdoor-detect-proc-obfuscated 0%
$0.49 6m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.00 <1m
lighttpd-backdoor-multiple-binaries-detect 0%
$0.29 12m
lighttpd-timebomb-multiple-binaries-detect 0%
$1.50 26m
sozu-backdoor-multiple-binaries-detect 0%
$0.23 7m
sozu-timebomb-multiple-binaries-detect 0%
$0.22 12m

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.