Coding agents now set each other's exam: GPT-5.5 fixes 98.3% of defects, Claude Opus 4.8 writes the hardest tasks
Coding-agent evaluation becomes a duel in which two agents author and solve each other's tasks: over 1,500 turns, GPT-5.5 with Codex CLI repaired 98.3% of the defects it reviewed, while Claude Opus 4.8 with mini-swe-agent was the strongest task author with a 27.3% Red win rate.