AI Model Reviewer

Claude Opus 5.5 in OpenCode 1.18.32

skills off

← Open in the gallerySame prompt, all models

Claude Opus 5.5's output for Tidewater

▶ Open live demo

Zoom, inline player and more ways to view
Poster frame of Claude Opus 5.5'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).

Recorded from the live demo (stepped clock). Preview video recorded by this site from the live demo. The moving picture above is that preview; the button runs the real page.

OKTidewatermax effortNeutral harness

Wall time 1h 58mCost $22.05 reported

Snapshot 1 of 1 saved during Claude Opus 5.5's run
Still snapshots saved during the run (the moving picture above was recorded from the live demo): 1 distinct frame.

Generation timelapse

Poster for generation timelapse

Generation timelapse (the agent's screen during the run, sped up). This is not the finished video. Download video (4.6 MB).

Review

No verdict yet.

The full review

OK. Finished on its own after 118.7 min.

Attempt 2 of 2

Every try of this model in this harness on this prompt, oldest first. This run is the cell's result.

  1. Attempt 1 Stopped by us42m 57s$3.592026-09-26
  2. Attempt 2 OK this run1h 58m$22.052026-09-26

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, 1,336 characters. Every result for this prompt

Build an explorable tropical island in Three.js. The island has white sand beaches, palm trees, a green hilly interior and a small fishing village of wooden huts with thatched roofs, joined to the sea by a long wooden pier with boats moored alongside. The ocean around it is animated, with waves, foam along the shore and clear shallow water over a reef where fish swim among corals and sea plants, fading to deep blue further out. Let the player switch between modes: walk on the island, swim at the surface, dive underwater (with underwater fog and caustic light), sail a small boat around the island, and fly a free camera. Add a time-of-day panel with a slider that moves the sun from morning through sunset to night, changing the sky, lighting and water colours, with stars and lit windows in the village at night. Show the controls on screen. Everything is built in code from Three.js geometry, shaders and materials; no external models or textures. Build it as index.html (plus any local asset files you create) in the current directory. Three.js may load from a pinned CDN. You may serve it locally and open it in headless chromium (/usr/bin/chromium, software WebGL, no GPU) to screenshot and inspect your own output, and iterate on your own before finishing. Close any browser you open as soon as you've taken your screenshot.

How it was made

Wall time 1h 58mFirst artifact at 28m 06s41 saved versions

Versions saved during the run

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

Version 41 of 41
  1. Version 1 at 28m 12s thumbnailv1 28:12
  2. Version 2 at 37m 00s thumbnailv2 37:00
  3. Version 3 at 42m 21s thumbnailv3 42:21
  4. Version 4 at 42m 31s thumbnailv4 42:31
  5. Version 5 at 44m 34s thumbnailv5 44:34
  6. Version 6 at 44m 44s thumbnailv6 44:44
  7. Version 7 at 49m 22s thumbnailv7 49:22
  8. Version 8 at 53m 19s thumbnailv8 53:19
  9. Version 9 at 54m 01s thumbnailv9 54:01
  10. Version 10 at 54m 16s thumbnailv10 54:16
  11. Version 11 at 55m 03s thumbnailv11 55:03
  12. Version 12 at 58m 00s thumbnailv12 58:00
  13. Version 13 at 59m 19s thumbnailv13 59:19
  14. Version 14 at 1h 00m thumbnailv14 1:00:49
  15. Version 15 at 1h 01m thumbnailv15 1:01:15
  16. Version 16 at 1h 03m thumbnailv16 1:03:23
  17. Version 17 at 1h 06m thumbnailv17 1:06:33
  18. Version 18 at 1h 06m thumbnailv18 1:06:49
  19. Version 19 at 1h 11m thumbnailv19 1:11:45
  20. Version 20 at 1h 15m thumbnailv20 1:15:35
  21. Version 21 at 1h 15m thumbnailv21 1:15:41
  22. Version 22 at 1h 18m thumbnailv22 1:18:55
  23. Version 23 at 1h 19m thumbnailv23 1:19:17
  24. Version 24 at 1h 21m thumbnailv24 1:21:30
  25. Version 25 at 1h 24m thumbnailv25 1:24:11
  26. Version 26 at 1h 26m thumbnailv26 1:26:35
  27. Version 27 at 1h 28m thumbnailv27 1:28:20
  28. Version 28 at 1h 33m thumbnailv28 1:33:56
  29. Version 29 at 1h 34m thumbnailv29 1:34:02
  30. Version 30 at 1h 34m thumbnailv30 1:34:30
  31. Version 31 at 1h 34m thumbnailv31 1:34:41
  32. Version 32 at 1h 34m thumbnailv32 1:34:47
  33. Version 33 at 1h 34m thumbnailv33 1:34:57
  34. Version 34 at 1h 35m thumbnailv34 1:35:03
  35. Version 35 at 1h 35m thumbnailv35 1:35:08
  36. Version 36 at 1h 37m thumbnailv36 1:37:57
  37. Version 37 at 1h 38m thumbnailv37 1:38:08
  38. Version 38 at 1h 38m thumbnailv38 1:38:14
  39. Version 39 at 1h 42m thumbnailv39 1:42:58
  40. Version 40 at 1h 49m thumbnailv40 1:49:14
  41. Version 41 at 1h 53m thumbnailv41 1:53:09

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 transcript is 38.7 MB; it is published as a scrubbed, compressed download rather than shown on the page.

Show all 395 steps

Loading the timeline…

Download the full transcript OpenCode session export, 427 KB, gzip. 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 $22.05, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $22.05.

Tokens by typeTokens$ per 1MCost
Input (uncached)334$4.00$0.0013
Cache write1,211,012$5.00$6.0551
Cache read28,407,290$0.20$5.6815
Output515,718$20.00$10.31
of which reasoning312,304billed as output
Total computed from tokens
$22.05
Total reported by the harness
$22.05
Difference
matches

OpenCode 1.18.32 reported its own total; token counts x list prices shown beside it. The harness reports reasoning tokens separately from output; here output includes them (203,414 visible + 312,304 reasoning), and both bill at the output rate.

Prices: Project price table (vendor list prices), 2026-09-22.

Run notes

one prompt, agentic harness (self-review allowed)prompt rewritten after the 2026-09-24 box losslabelled re-run (of threejs_tidewater__opencode__opus-5-5)

  • frozen prompt (rewritten): engine/prompts_rewritten/threejs_tidewater.txt: written by us from the recorded description (zero results)
  • plain OpenCode config copy (providers only; no ECC instructions/agents)
  • opencode export written to a file (not piped)
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation audit: outside paths seen