Introducing GPT-5.2-Codex
Open paper
Benchmark
Model
Rank
Results
code-generation-on-swe-bench-pro
GPT-5.2-Codex
–
Resolved: 56.4
code-generation-on-swe-bench-pro
gpt-5.2-codex
–
Resolved: 41.04
Rank counts only results with a code link.