One-shot a Minecraft-style voxel game in three.js
Exact prompt
In one pass, build a playable Minecraft-style voxel game as a single file index.html using three.js loaded from https://unpkg.com/three@0.160.0/build/three.module.js (ES module import). Requirements: a generated terrain of at least 32x32 columns with at least 3 block types; first-person WASD movement with mouse look (pointer lock); left click breaks the targeted block, right click places a block; number keys 1-3 select block type; a crosshair and a small HUD showing the selected block. No other files.
Task prompt given to the agent (headless, offline, synthetic fixture inputs): In one pass, build a playable Minecraft-style voxel game as a single file index.html using three.js loaded from https://unpkg.com/three@0.160.0/build/three.module.js (ES module import). Requirements: a generated terrain of at least 32x32 columns with at least 3 block types; first-person WASD movement with mouse look (pointer lock); left click breaks the targeted block, right click places a block; number keys 1-3 select block type; a crosshair and a small HUD showing the selected block. No other files. Inspired by https://x.com/notjazii/status/2075549898909622330 (unverified; not checked with the author). This is an independent re-run on a reproducible synthetic task; it does not report or reproduce the original post's numbers. Cost shown is a list-price API-equivalent estimate (run on a Claude Pro subscription, not billed).
Success criteria: All automated rubric checks pass: imports three@0.160.0 module; pointer lock; WASD; raycast break/place (mouse buttons 0 and 2); block select keys 1-3; crosshair + HUD elements; terrain >=32x32 (size constant); no uncaught console errors in headless Chrome.
Best model for this task so far: Gemma 4 31B Instruct (Venice) (success, $0.0032, 7m). Best AI model for Games & Simulations →
All runs (9)
78% pass rate across 9 eligible runs: 7 pass, 0 partial, 2 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| ZGLM 5.3 (Venice)thinking on | $0.17 | 5m | 0 | Fully autonomous | fail | Trust 80% | 2026-10-17 | |
| AClaude Haiku 5.5default · thinking on | $0.02 | 2m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-16 | |
| DDeepSeek V4.1 Flash (Venice)thinking off | $0.04 | 3m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| XGrok 4.3 (Venice) | $0.02 | 31s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| QQwen3 Coder 480B Turbo (Venice) | $0.0049 | 27s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-15 | |
| GGemma 4 31B Instruct (Venice) | $0.0032 | 7m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| DDeepSeek V4.1 Flash (Venice) | $0.04 | 2m | 0 | Fully autonomous | fail | Trust 80% | 2026-10-14 | |
| AClaude Opus 5.5 | $0.56 | 2m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 | |
| AClaude Sonnet 5.5 | $0.09 | 27s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-14 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.