oneshotlm
← What's new
New Models

Added GLM-5.2, MiMo v2.5 and 3 more models

Five more models joined the matrix this week, and we re-ran every prompt against them. The alien-shooter build is a good stress test: it needs a game loop, collision, and input handling all in one file, so the gap between models shows up fast.

DeepSeek-V4-Pro shipped a playable loop on the first try, while several of the cheaper models stalled on a blank canvas or a control panel that never wired up. Open any tile below to see the live build and the full transcript.

Top builds in this update

deepseek-v4-pro — Top-down alien shooter CLEAN
deepseek-v4-pro Top-down alien shooter
Generated pi-agent · 196.2s · $0.0170 · 9.6k out
Evaluated working idle 1.3% ·click 3.0%·drag 2.8%

“Top-down alien shooter with ship, aliens, HP/score/kills HUD, and functioning game-over/restart screen.”— vision grade, anthropic/claude-sonnet-5

Full run + transcript →
kimi-k2.7-code — Top-down alien shooter PARTIAL
kimi-k2.7-code Top-down alien shooter
Generated pi-agent · 699.9s · $0.1491 · 20k out
Evaluated partial idle 0.0% ·click 0.0%·drag 0.0%

“Menu starts game, aliens spawn and move, but WASD input crashed the game leading to Game Over screen almost instantly.”— vision grade, anthropic/claude-sonnet-5

Full run + transcript →
glm-5.2 — Top-down alien shooter BROKEN
glm-5.2 Top-down alien shooter
Generated pi-agent · 476.7s · $0.2385 · 25k out
Evaluated broken idle 0.0% ·click 0.0%·drag 0.0%

“Game already over before any input; stuck on Game Over screen, unresponsive to R restart or any input attempted.”— vision grade, anthropic/claude-sonnet-5

Full run + transcript →
minimax-m2.7 — Top-down alien shooter BLANK
minimax-m2.7 Top-down alien shooter
Generated pi-agent · 146.6s · $0.0098 · 6.2k out
Evaluated broken idle 0.0% ·click 0.0%·drag 0.0%

“Blank black canvas throughout; JS error 'Phaser.Graphics is not a constructor' prevented the game from rendering.”— vision grade, anthropic/claude-sonnet-5

Full run + transcript →