bug-bounty413
xss277
google249
microsoft215
facebook191
apple139
rce124
malware101
bragging-post92
account-takeover88
exploit86
csrf73
cve70
authentication-bypass67
privilege-escalation60
access-control53
phishing48
defi48
dos47
smart-contract47
ethereum44
writeup44
open-source43
supply-chain42
ssrf42
cloudflare42
sql-injection41
browser40
web339
stored-xss39
aws37
web-security36
docker36
input-validation36
ai-agents35
api-security34
smart-contract-vulnerability33
reverse-engineering32
react32
information-disclosure31
idor31
burp-suite30
oauth29
denial-of-service29
cross-site-scripting29
node28
reflected-xss28
race-condition27
web-application27
clickjacking25
0
2/10
Cursor describes CursorBench, an internal evaluation suite for measuring AI coding agent quality using real developer workflows rather than public benchmarks. The approach combines offline evals on private task data with online metrics to better distinguish between models and align with actual developer experience.
Cursor
CursorBench
SWE-bench Verified
OpenAI
GPT-5
Haiku
Cursor Blame