Atlas

Benchmarks

← All benchmarks

CWE-bench v2: Cryptography and Secrets

Cybersecurity · 2026-11-02

Pass@1 on the 28 tasks of Collinear AI's K06 weakness class in CWE-bench v2, rounded to a whole point by the publisher. The ten classes are the publisher's own grouping, not an official taxonomy.

Benchmark source: Cwe Bench

Top models (higher is better)

ModelScoreSource
GPT-6 Astra79.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Muse Wonder75.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Claude Opus 5.572.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Gemini 4 Argon70.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Grok 4.763.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
DeepSeek V4.1 Flash 101754.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Mistral Large 4 Preview53.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Hy4 Preview52.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Qwen3.8 Max (0902)50.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Kimi K3.1 Pro48.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
GLM-5.343.0CWE-bench v2 leaderboard (snapshot 2026-11-03) · Collinear AI
Loading Atlas data…