AI Model Reviewer

MiniMax M3 in OpenCode 1.18.35

skills on · OpenCode 1.18.35 + skills on (54: 33 video + 21 web/Three.js)Kit: 33 video + 21 web/Three.js · 3 of 54 installed skills used in the session

← Open in the gallerySame prompt, all models

Zoom, inline player and more ways to view
Poster frame of MiniMax M3's page
Open the original page

The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. It starts in its auto-tour (T switches to play mode on a keyboard).

OKMobile touch arcade gamemax effortNeutral harness

Wall time 18m 45sCost $0.55 reported

Review

No verdict yet.

The full review

OK. Finished on its own after 18.8 min.

Scores

AI judge

Not scored

No rubric for this prompt

Visitor votes and reviewer grades are not available yet.

AI judge
AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
Visitors
Public voting with a blind reveal is coming: you score the output first, then see the other scores.
Reviewer
The reviewer's own grade appears here once it is added.

Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.

Downloads

Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.

The exact prompt

as run, 594 characters. Every result for this prompt

Build a complete, polished mobile-first 3D arcade game in Three.js as one self-contained index.html (no external assets; all geometry, textures and sound procedural). Portrait orientation, touch controls (swipe/drag and tap) with keyboard fallback for desktop. Include a title screen, at least 3 increasing difficulty phases, score and best-score persistence in localStorage, juicy feedback (screen shake, particles, procedural Web Audio sfx), pause/resume when the tab is hidden, and a game-over screen with restart. Must hold 60 fps on a mid-range phone; keep draw calls low with instancing.

How it was made

Wall time 18m 45sFirst artifact at 3m 55s12 saved versions

Versions saved during the run

12 intermediate outputs, in the order the model wrote them.

Step by step

The prompt, every agent turn and tool call (tool name and a one-line summary; inputs and outputs are not shown), then the final message. The full machine-format transcript is published as a scrubbed download.

Show all 155 steps

Loading the timeline…

Download the full transcript OpenCode session export, 708 KB. Scrubbed: anything that looks like a key, token, e-mail address or phone number is replaced, and account details and the test machine's file paths are removed.

Cost breakdown

Headline cost $0.55, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $0.54.

Tokens by typeTokens$ per 1MCost
Input (uncached)129,226$0.30$0.0388
Cache write0$0.30$0
Cache read6,851,241$0.06$0.4042
Output81,479$1.20$0.0978
of which reasoning34,915billed as output
Total computed from tokens
$0.5408
Total reported by the harness
$0.5476
Difference
computed $0.54 vs reported $0.55 (diff -0.01)

OpenCode 1.18.35 reported its own total; token counts x list prices shown beside it. The harness reports reasoning tokens separately from output; here output includes them (46,564 visible + 34,915 reasoning), and both bill at the output rate.

Prices: https://fireworks.ai/models/fireworks/minimax-m3, 2026-10-08.

Run notes

one prompt, agentic harness (self-review allowed)skills=on

  • frozen prompt (written): core requirements sha256 951df6284d51, full harness prompt sha256 951df6284d51; exact prompt text used by the existing harness rows of this test on the runs branch (copied from threejs_mobile_touch_arcade_game__claude-code__opus-5-5-high__attempt1/meta.json, sha256 verified); Bet
  • no TUI: the harness ran in its non-interactive mode, so there are no TUI screenshots; the timelapse is built from version renders only
  • OpenCode config (providers only, permission allow-all except question; no agents/instructions) + both default skill kits in xdg/config/opencode/skill (skills=on)
  • infra retries: 0
  • in the published transcript the sandbox HOME directory is shown as <HOME>
  • skills=on: 54 skills installed in the harness skill directory before launch (video-33 remotion-dev/skills + heygen-com/hyperframes@0b5db9da + f; web-threejs-21 [redacted]/ai-AI Model Reviewer skills/ (alpha/mr-homebar)@7521074d98c9).
  • Mode: headless run mode (opencode run --format json), inside bubblewrap sandbox
  • Isolation audit: paths_seen
  • Renderer: Three.js r160 (three@0.160.1 module loaded from unpkg through an importmap) with WebGLRenderer; extra 2D canvases created by the page's script; sound through WebAudio.
  • Card video: the run's own video.mp4 (H.264 yuv420p, unchanged). Poster: the run's own render.png.
  • Skills on: the run had 54 skills installed (33 video + 21 web/Three.js), as its meta records.
  • MiniMax M3 served via Fireworks (OpenCode provider fireworks-ai).
  • Same frozen prompt as the other rows on this test; configurations differ and all rows are unscored, so this is not a head-to-head result.