Live data from Hacker News

We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

Post reply on HN

Print view View original

1–5 of 5 posts

We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

#1

Post by geopsist » Thu, May 28, 2026, 12:39 PM UTC

We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs
trent.ai

Re: We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

#2

Post by brammertottens » Thu, May 28, 2026, 12:42 PM UTC

[flagged]

Re: We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

#3

Post by geopsist » Thu, May 28, 2026, 12:57 PM UTC

[flagged]

Re: We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

#4

Post by enothereska » Thu, May 28, 2026, 1:22 PM UTC

I'm co-founder at trent.ai, happy to answer any questions around this.

Re: We Benchmarked Claude Code, Codex, Semgrep, CodeQL, Trent on 28 CWE-Bench CVEs

#5

Post by kbrajesh176 » Fri, May 29, 2026, 8:29 AM UTC

Looks interesting. LLM base solutions fails when metric is strict. For security solution guess is not enough, we need reliable and robust solution to pin vulnerability and its evidence to fully judge and mitigate with appropriate fix.

Post reply on HN