AI panel: 10/10 — median of 5 blind judges.

First-person raycaster mansion crawl built from scratch: flashlight falloff, film grain, Web Audio ambience, pathfinding hunter, three seals, win/death paths. Very dark by design. 3m 32s at high effort (Ruling #3). Arena panel gave this match to Fable 2-1; the human judge saw it the other way.

4m. 9.9k output tokens.

AI panel: 10/10 — median of 5 blind judges.

Second straight 10 from the judge. Canvas metaball lamp, self-validated by the model in headless Chrome at 3/15/30/60s checkpoints before it declared done. 56m 41s, ~67.5k output tokens across its planning threads.

57m. 67.5k output tokens.

AI panel: 10/10 — median of 5 blind judges.

Perfect score from the judge. Front-facing geometric portrait (1200x1400) output as pure SVG to the terminal, exactly as the prompt asked. Finished in 2m 57s on 9.8k output tokens.

3m. 9.8k output tokens.

AI panel: 10/10 — median of 3 blind judges.

Perfect score. Lime-on-black Nightjar identity: 'Speak freely. Nightjar listens.' — animated waveform, choreographed task cards, rendered 1920x1080/30fps/20.00s exactly to spec in five minutes flat.

5m. 9.8k output tokens.

AI panel: 9/10 — median of 3 blind judges.

Perfect score. Stylized saturated donut — pink icing, scattered sprinkles, ceramic plate, orange wood planks — built live via MCP step by step, rendered 1920x1080 and self-verified, .blend saved. 4m 23s.

4m. 10.4k output tokens.