BinaryAudit / claude-sonnet-4.5

Anthropic anthropic 49% pass rate Rank #4 of 16 Proprietary 29 Sept 2025

Total Runs

97

Tasks Tested

33

Total Cost

$69.52

Avg Duration

9.3m

Performance by Task

Task Pass Rate Runs Avg Cost Avg Time
dnsmasq-backdoor-detect-negative 100%
$0.92 8m
dnsmasq-backdoor-detect-negative2 100%
$1.01 12m
dnsmasq-backdoor-detect-printf 100%
$0.57 7m
GHIDRA_FAV150 ghidra-decompile-pyghidra 100%
$0.27 7m
GHIDRA_FAV150 ghidra-decompile-pyghidra-jq 100%
$0.19 9m
GHIDRA_FAV150 ghidra-decompile-vanilla 100%
$0.30 5m
lighttpd-backdoor-detect-negative 100%
$0.33 4m
lighttpd-backdoor-detect-negative2 100%
$0.51 7m
radare2-decompile 100%
$0.07 2m
radare2-decompile-jq 100%
$0.13 3m
sozu-backdoor-detect-negative 100%
$0.29 4m
sozu-backdoor-detect-negative2 100%
$0.39 4m
dnsmasq-backdoor-detect-obfuscated 67%
$0.58 7m
dnsmasq-backdoor-detect-syscall 67%
$0.61 6m
GHIDRA_FAV150 ghidra-decompile-vanilla-jq 67%
$0.40 14m
lighttpd-backdoor-detect-open 67%
$1.05 11m
lighttpd-timebomb-multiple-binaries-detect 67%
$0.38 6m
dnsmasq-backdoor-detect 33%
$0.92 8m
dropbear-brokenauth-detect 33%
$0.61 6m
lighttpd-backdoor-multiple-binaries-detect 33%
$0.52 9m
sozu-backdoor-multiple-arch-binaries-detect 33%
$1.16 17m
dnsmasq-backdoor-detect-execvp-obfuscated 0%
$0.88 7m
dnsmasq-backdoor-detect-posix-spawn 0%
$1.12 11m
dnsmasq-backdoor-detect-posix-spawn-obfuscated 0%
$0.83 7m
dnsmasq-backdoor-detect-syscall-obfuscated 0%
$0.90 11m
dropbear-brokenauth-detect-negative 0%
$0.73 6m
dropbear-brokenauth-detect-negative2 0%
$0.67 9m
dropbear-brokenauth-detect-nologline 0%
$0.31 3m
dropbear-brokenauth2-detect 0%
$0.71 6m
lighttpd-backdoor-detect-proc-obfuscated 0%
$1.30 10m
lighttpd-backdoor-multiple-arch-binaries-detect 0%
$0.00 <1m
sozu-backdoor-multiple-binaries-detect 0%
$1.05 25m
sozu-timebomb-multiple-binaries-detect 0%
$3.66 53m

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.