Introducing GPT-5.5
Open paper
Benchmark
Model
Rank
Results
code-generation-on-swe-bench-pro
GPT-5.5
–
Resolved: 58.6
code-generation-on-terminal-bench-2-1
Terminus-2 + GPT-5.5
–
Accuracy: 84.0
Rank counts only results with a code link.