AI Model Reviewer

Claude Fable 5.1 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 Fable 5.1'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.

OKHash table showdownmax effortNeutral harness

Wall time 41m 11sCost $16.72 estimated

Review

No verdict yet.

The full review

OK. Finished on its own after 41.2 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, 2,033 characters. Every result for this prompt

Build a hash table collision showdown: four hash tables of 31 buckets each receive the same stream of string keys (words like city names) at the same time, one insert per tick, using separate chaining, linear probing, quadratic probing and cuckoo hashing with two tables. Show each key flying in, the computed hash value as a number, every probe step as a hop between buckets, chains growing as stacks, clusters forming in linear probing (highlight primary clusters), and cuckoo evictions as keys being kicked out and flying to their alternate slot. Each panel shows live load factor, average and worst probe count, and total probes. When a table passes its load-factor limit (0.75 for open addressing, 0.9 for cuckoo, chaining never), animate a resize to the next prime size with every key re-hashed into place. Every 20 inserts, run a burst of 10 lookups (half present, half missing) and show their probe paths. Controls: key stream presets (city names, sequential numbers as strings, adversarial keys that collide under the default hash), choice of hash function (djb2, FNV-1a, a deliberately bad sum-of-chars), speed slider, play, pause, step, reset. So the page is alive without input, on load it starts streaming the city names automatically and after the stream finishes it waits 3 seconds and moves to the next preset, forever, until the user touches a control. Make it clear enough to teach and pretty enough to watch.

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 41m 11sFirst artifact at 19m 46s3 saved versions

Versions saved during the run

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

Version 5 of 3
  1. Version 1 at 19m 47s thumbnailv1 19:47
  2. Version 3 at 29m 32s thumbnailv3 29:32
  3. Version 5 at 36m 05s thumbnailv5 36:05

No transcript was delivered with this result.

Cost breakdown

Headline cost $16.72, estimated from the token counts at list price.

Tokens by typeTokens$ per 1MCost
Input (uncached)644$10.00$0.0064
Cache write441,991$12.50$5.5249
Cache read4,044,634$0.25$1.0112
Output203,461$50.00$10.17
of which reasoning141,061billed as output
Total computed from tokens
$16.72
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)

  • frozen prompt (written): written 2026-10-05 for the MR category expansion (owner request: 500 finished runs in every category); category algorithm_visualizers; 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
  • Renderer: Canvas 2D (getContext('2d') at index.html line 872); single self-contained index.html, no CDN and no external assets.
  • Card video: the run's own 8 s session capture (headless Chromium, no GPU), re-encoded as H.264. Poster: the run's own render.png.