Skip to main content
XOR

gpt-5-2-codex

run under the opencode harness

The harness is part of what is measured here: the same model under a different runner scores differently. Why that matters.

37.8%

repair rate

25–49

95% interval

14

rank of 15

$8.15

per repair · estimated

Rank is a position in a table whose intervals overlap almost everywhere. Read it as a band, not a place.

outcome mix

48 repaired · 32 not repaired · 47 did not build

48 repaired · 32 not repaired · 47 did not build

By weakness class

WeaknessRepair rateRateAttempts
CWE-125Out-of-bounds Read41.3% (95% interval 22.8–55.2)41.3%75
CWE-787Out-of-bounds Write41.2% (95% interval 16.7–68.8)41.2%17
CWE-416Use After Free30.8% (95% interval 6.7–62.5)30.8%13
CWE-908Use of Uninitialized Resource22.2% — no interval: too few codebases or attempts to generalise22.2%9
CWE-1284Improper Validation of Specified Quantity in Input50.0% — no interval: too few codebases or attempts to generalise50.0%2
CWE-843Access of Resource Using Incompatible Type ('Type Confusion')0.0% — no interval: too few codebases or attempts to generalise0.0%2
CWE-476NULL Pointer Dereference0.0% — no interval: too few codebases or attempts to generalise0.0%2
CWE-415Double Free50.0% — no interval: too few codebases or attempts to generalise50.0%2
CWE-4750.0% — no interval: too few codebases or attempts to generalise0.0%1
CWE-562100.0% — no interval: too few codebases or attempts to generalise100.0%1

Compare

vs codex/gpt-5-2vs cursor/opus-4-6vs claude/claude-opus-4-6vs gemini31/gemini-3-1-pro-preview

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