AI Model Reviewer

Kimi K3 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 · 4 of 54 installed skills used in the session

← Open in the gallerySame prompt, all models

Stopped by us

We ended the run ourselves before any output. Not a model failure.

Stopped by usImpressionist worldn/a effortNeutral harness

Wall time 45m 01sCost $2.10 reported

Review

No verdict yet.

The full review

Stopped by us. Stopped by us (box row cap reached (2700s); stopped by the box lane so the run ships as partial); not a model failure.

Scores

Not scored: only runs that finished on their own are scored.

Downloads

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

The exact prompt

as run, 1,074 characters. Every result for this prompt

Build a real-time 3D world in Three.js that looks like a living impressionist oil painting (one HTML file, CDN imports only, no external assets or textures; everything procedural). The whole frame must read as painted, not as a 3D render with a filter: a brush-stroke post-process (oriented, varied-size strokes that follow surface direction and color, visible canvas grain), a painterly sky with broken-color clouds, water with dappled reflections of the sky and shore, and a small landscape (garden, footbridge or shoreline, trees, flowers). Add falling snow that is painted too, and flocks of birds flying through the scene. Include two or three painted figures; clicking one opens a short in-world dialogue in a hand-lettered caption style. Interactive camera (orbit plus a gentle walk mode), a time-of-day slider that shifts the palette from cool morning to warm dusk, and a toggle that compares the painted view with the plain render. Must stay smooth on a laptop and usable on a phone (touch controls, adaptive quality). It should feel like stepping into a painting.

How it was made

Wall time 45m 01sFirst artifact at 32m 40s

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 38 steps

Loading the timeline…

Download the full transcript OpenCode session export, 539 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 $2.10, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $2.10.

Tokens by typeTokens$ per 1MCost
Input (uncached)152,525$3.00$0.4576
Cache write0$3.00$0
Cache read1,460,851$0.30$0.4383
Output80,587$15.00$1.2088
of which reasoning38,221billed as output
Total computed from tokens
$2.1046
Total reported by the harness
$2.1046
Difference
matches

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 (42,366 visible + 38,221 reasoning), and both bill at the output rate.

Prices: https://platform.kimi.ai/docs/pricing/chat, 2026-09-24.

Run notes

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

  • frozen prompt (written): core requirements sha256 1ddb514daa65, full harness prompt sha256 1ddb514daa65; exact prompt text used by the existing harness rows of this test on the runs branch (copied from threejs_impressionist_world__claude-code__opus-5-5-high__attempt1/meta.json, sha256 verified); Beta hal
  • 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: none
  • Renderer: three.js r160 WebGL (ES module via an importmap) loaded from the jsDelivr CDN plus Google Fonts, so the page is not fully self-contained; custom shaders; canvas 2D only for textures.
  • Status: stopped by us. Stopped at the row cap (45 min) before the harness declared it finished; the page shown is what it had built by then.
  • Skills on: the run had 54 skills installed (33 video + 21 web/Three.js), as its meta records.
  • Kimi K3 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.
  • Live demo: not published. The page it had written by the stop throws a WebGL shader compile error on load in any browser: its own fragment shader defines RRTAndODTFit, which three.js r160 already injects for ACESFilmicToneMapping, so the scene does not render. Poster: a headless-Chromium screenshot of that page taken at import (the run folder has no render.png).