NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to select from k=8 weak-model proposals using execution and proof signals. What does
Paper: GPT-5.4 Nano with Critic-Comparator Reaches SWE-bench Parity
By
–
