AI Model Reviewer

Claude Opus 5.5 in Claude Code 2.1.280

skills off

← Open in the gallerySame prompt, all models

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. Tap inside for sound.

OKSpreadsheethigh effortNeutral harness

Wall time 12m 42sCost $2.62 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 12.7 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, 1,892 characters. Every result for this prompt

Build a working mini spreadsheet app in one web page. It needs a grid with column letters A to Z and row numbers 1 to 50, a formula bar that shows the raw content of the selected cell, and editing by typing or double-clicking. Cells hold numbers, text or formulas starting with =. Formulas support + - * / and parentheses, cell references (A1), ranges (A1:B5) and the functions SUM, AVERAGE, MIN, MAX and COUNT; every dependent cell recalculates instantly when a referenced cell changes. Show #REF! for a bad reference, #DIV/0! for division by zero and #CIRC! for a circular reference instead of hanging. Support selecting a rectangular range by dragging or shift-clicking, with a status bar showing that range's sum, average and count; copy and paste within the grid (references in pasted formulas shift relative to the move); bold and number-format buttons (plain, 2 decimals, currency, percent); and a save to and load from localStorage. So the first view is meaningful, on load the sheet opens with a household budget already filled in: twelve expense rows with monthly amounts, a total row and an average row built with formulas, and a percent-of-total column built with formulas, all computed live. Make it look like a clean modern spreadsheet that is usable on desktop and phone.

Save it as index.html in the current directory: one self-contained file with inline CSS and JavaScript only, no libraries or frameworks, and no external requests of any kind (no CDNs, web fonts, images or audio files). It must work when opened directly from disk, fit any window from a 390 px wide phone to a desktop, and run without console errors. 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 12m 42sFirst artifact at 8m 49s3 saved versions

Versions saved during the run

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

Version 3 of 3
  1. Version 1 at 8m 52s thumbnailv1 8:52
  2. Version 2 at 9m 17s thumbnailv2 9:17
  3. Version 3 at 12m 19s thumbnailv3 12:19

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

Show all 29 steps

Loading the timeline…

Download the full transcript Claude Code session JSONL, 102 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 $2.62, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)40$4.00$0.0002
Cache write147,590$5.00$0.7379
Cache read1,819,491$0.20$0.3639
Output75,661$20.00$1.5132
of which reasoning37,394billed as output
Total computed from tokens
$2.6152
Total reported by the harness
none

Computed from harness-reported token counts x list prices.

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

Run notes

one prompt, agentic harness (self-review allowed)labelled re-run (of appclone_spreadsheet__claude-code__opus-5-5-high)

  • frozen prompt (written): written 2026-10-01 for the MR new-categories expansion (owner request: expand model review with new kinds of tests); category app_clones; zero results
  • plain wave-1-equivalent cc_config copy (settings.json + .claude.json; no ECC files)
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Context setting: 1M ([1m] model name)
  • Isolation audit: none