Skip to main content

claude-opus-4-6 vs gpt-5.2-codex

Both models ran the same corpus under the same verifier — claude and opencode respectively. The harness differs where the names differ, and that is part of what separates them.

claude-opus-4-6 leads by 23.8 points, and the intervals do not overlap.

claude / claude-opus-4-6

61.6%

95% interval 48.9–71.3 · 125 attempts

61.6% (95% interval 48.9–71.3)
Full profile →

opencode / gpt-5.2-codex

37.8%

95% interval 25.0–48.7 · 127 attempts

37.8% (95% interval 25.0–48.7)
Full profile →

Where they differ

Weaknessclaude-opus-4-6gpt-5.2-codexDifference
CWE-125Out-of-bounds Read69.3%41.3%+28.0
CWE-787Out-of-bounds Write50.0%41.2%+8.8
CWE-416Use After Free63.6%30.8%+32.8
CWE-908Use of Uninitialized Resource11.1%22.2%-11.1
CWE-415Double Free66.7%50.0%+16.7
CWE-1284Improper Validation of Specified Quantity in Input50.0%50.0%0.0
CWE-843Access of Resource Using Incompatible Type ('Type Confusion')50.0%0.0%+50.0
CWE-476NULL Pointer Dereference50.0%0.0%+50.0
CWE-475100.0%0.0%+100.0
CWE-562100.0%100.0%0.0

Per-class samples are small; a difference here is a hint about where to look, not a result. The corpus-level intervals above are the honest comparison.

Corpus cve-bench-136 · run February 2026 · How we test

See the benchmark →