Lianhui Qin#721
We gave 4 frontier coding agents the same hard environment-gen test:
Preserve the desert landscape. Surgically remove only the ruins. Then build a dense, believable Middle Eastern village from scratch using rustic assets.
Which model did the best job? 🏜️👇
Poll and full prompt in thread.
Users express enthusiasm for Claude Opus topping AI coding agents by urging votes for the best performer in the test.
I think Claude Code may have won on quality, but it came at a cost: 14× the runtime of Cursor.
Gemini is interesting here, not the absolute best, but maybe the best balance between quality and speed.
We gave 4 frontier coding agents the same hard environment-gen test:
Preserve the desert landscape. Surgically remove only the ruins. Then build a dense, believable Middle Eastern village from scratch using rustic assets.
Which model did the best job? 🏜️👇
Poll and full prompt in thread.
Vote the best!
Lianhui Qin#721We gave 4 frontier coding agents the same hard environment-gen test:
Preserve the desert landscape. Surgically remove only the ruins. Then build a dense, believable Middle Eastern village from scratch using rustic assets.
Which model did the best job? 🏜️👇
Poll and full prompt in thread.