Skip to main content
How it works
Benchmarks
Blog
About us
Token economics
Talk to the founder
How it works
Benchmarks
Blog
About us
Token economics
Talk to the founder
BinaryAudit
/
GPT-5.2
OpenAI
openai
48% pass rate
Rank #12 of 26
Proprietary
11 Dec 2025
Total Runs
94
Tasks Tested
32
Total Cost
$47.55
Avg Duration
15.8m
Performance by Task
Task
Pass Rate
Runs
Avg Cost
Avg Time
dnsmasq-backdoor-detect-negative
100%
$0.57
24m
dnsmasq-backdoor-detect-negative2
100%
$0.37
15m
dropbear-brokenauth-detect-negative
100%
$0.38
13m
dropbear-brokenauth-detect-negative2
100%
$0.53
15m
GHIDRA_FAV150
ghidra-decompile-pyghidra
100%
$0.28
8m
GHIDRA_FAV150
ghidra-decompile-vanilla
100%
$0.32
8m
lighttpd-backdoor-detect-negative
100%
$0.17
3m
lighttpd-backdoor-detect-negative2
100%
$0.16
4m
radare2-decompile
100%
$0.09
3m
radare2-decompile-jq
100%
$0.12
3m
sozu-backdoor-detect-negative
100%
$0.41
11m
dnsmasq-backdoor-detect-obfuscated
67%
$0.71
22m
dnsmasq-backdoor-detect-posix-spawn
67%
$0.38
15m
GHIDRA_FAV150
ghidra-decompile-pyghidra-jq
67%
$0.44
16m
GHIDRA_FAV150
ghidra-decompile-vanilla-jq
67%
$0.82
22m
dnsmasq-backdoor-detect
33%
$0.48
17m
dnsmasq-backdoor-detect-execvp-obfuscated
33%
$0.30
12m
dnsmasq-backdoor-detect-syscall
33%
$0.75
22m
lighttpd-backdoor-multiple-binaries-detect
33%
$0.93
21m
lighttpd-timebomb-multiple-binaries-detect
33%
$0.76
19m
sozu-backdoor-multiple-arch-binaries-detect
33%
$0.73
24m
dnsmasq-backdoor-detect-posix-spawn-obfuscated
0%
$0.93
30m
dnsmasq-backdoor-detect-printf
0%
$0.45
17m
dnsmasq-backdoor-detect-syscall-obfuscated
0%
$0.61
23m
dropbear-brokenauth-detect
0%
$0.34
11m
dropbear-brokenauth-detect-nologline
0%
$0.22
10m
dropbear-brokenauth2-detect
0%
$0.51
20m
lighttpd-backdoor-detect-open
0%
$0.25
9m
lighttpd-backdoor-detect-proc-obfuscated
0%
$0.32
11m
lighttpd-backdoor-multiple-arch-binaries-detect
0%
$0.00
<1m
sozu-backdoor-multiple-binaries-detect
0%
$0.92
24m
sozu-timebomb-multiple-binaries-detect
0%
$1.87
54m