Atomic.chat says Qwen 3.7-max beat Opus 4.7 and GPT-5.5 in agentic Tetris-bot test

In a 10-iteration code-and-rewrite challenge, the team let each model build and train a Tetris bot, then compared the final agents.

By · Published

Screenshot of Qwen 3.7 Max beating Opus and GPT 5.5 at making a functioning Tetris game

In a 10-iteration code-and-rewrite challenge, the team let each model build and train a Tetris bot, then compared the final agents.