Skip to main content
How it works
Benchmarks
Blog
About us
Token economics
Talk to the founder
Menu
How it works
Benchmarks
Blog
About us
Token economics
Talk to the founder
BinaryAudit
/
GPT-5.4 XHigh
OpenAI
openai
41% pass rate
Rank #17 of 26
Proprietary
5 Mar 2026
Total Runs
99
Tasks Tested
33
Total Cost
$140.71
Avg Duration
59.0m
Performance by Task
Task
Pass Rate
Runs
Avg Cost
Avg Time
GHIDRA_FAV150
ghidra-decompile-vanilla
100%
$1.30
22m
lighttpd-backdoor-detect-negative
100%
$1.55
24m
lighttpd-backdoor-detect-negative2
100%
$0.72
12m
radare2-decompile
100%
$0.53
8m
sozu-backdoor-detect-negative
100%
$0.99
16m
dnsmasq-backdoor-detect-negative
67%
$0.97
53m
dnsmasq-backdoor-detect-posix-spawn
67%
$1.63
26m
dnsmasq-backdoor-detect-syscall
67%
$1.80
92m
dropbear-brokenauth-detect-negative
67%
$2.18
69m
GHIDRA_FAV150
ghidra-decompile-pyghidra
67%
$0.64
50m
GHIDRA_FAV150
ghidra-decompile-pyghidra-jq
67%
$0.61
51m
GHIDRA_FAV150
ghidra-decompile-vanilla-jq
67%
$0.71
51m
lighttpd-timebomb-multiple-binaries-detect
67%
$2.01
65m
radare2-decompile-jq
67%
$0.61
50m
sozu-backdoor-detect-negative2
67%
$1.20
52m
dnsmasq-backdoor-detect
33%
$1.21
54m
dnsmasq-backdoor-detect-negative2
33%
$1.40
60m
dnsmasq-backdoor-detect-posix-spawn-obfuscated
33%
$2.61
74m
dropbear-brokenauth-detect
33%
$1.84
70m
dropbear-brokenauth-detect-negative2
33%
$1.90
95m
lighttpd-backdoor-multiple-binaries-detect
33%
$1.13
17m
dnsmasq-backdoor-detect-execvp-obfuscated
0%
$1.26
58m
dnsmasq-backdoor-detect-obfuscated
0%
$1.31
90m
dnsmasq-backdoor-detect-printf
0%
$0.94
53m
dnsmasq-backdoor-detect-syscall-obfuscated
0%
$1.86
60m
dropbear-brokenauth-detect-nologline
0%
$1.47
93m
dropbear-brokenauth2-detect
0%
$1.92
95m
lighttpd-backdoor-detect-open
0%
$1.77
91m
lighttpd-backdoor-detect-proc-obfuscated
0%
$1.05
54m
lighttpd-backdoor-multiple-arch-binaries-detect
0%
$1.29
56m
sozu-backdoor-multiple-arch-binaries-detect
0%
$2.26
108m
sozu-backdoor-multiple-binaries-detect
0%
$1.94
120m
sozu-timebomb-multiple-binaries-detect
0%
$2.27
60m