AI Model Reviewer

DeepSeek V4.1 Flash in OpenCode 1.18.32

skills off

← Open in the gallerySame prompt, all models

DeepSeek V4.1 Flash's output for Isometric SVG town with sprite sheet

▶ Open live demo

Zoom, inline player and more ways to view
DeepSeek V4.1 Flash's SVG for Isometric SVG town with sprite sheet

Showing a WebP render of the 262 KB SVG so the page loads fast; zooming loads the SVG itself.

OKIsometric SVG town with sprite sheetmax effortNeutral harness

Wall time 26m 14sCost $0.23 reported9.0/10 · Draft score — stored total; criterion breakdown unavailable

Open the SVG filePoster render (WebP)

Review

Tidy isometric village "Willowbrook": a <defs> building set reused 78 times, 25+ houses, a castle keep, a windmill, a market fountain, lanes, trees, and a river with a stone arch bridge and a waterfall off the slab, all in one consistent soft palette.

The full review

Tidy isometric village "Willowbrook": a <defs> building set reused 78 times, 25+ houses, a castle keep, a windmill, a market fountain, lanes, trees, and a river with a stone arch bridge and a waterfall off the slab, all in one consistent soft palette. Around the river, the oversized grey bridge deck and the stacked wooden jetties overlap each other and the water in a confusing way, which is the only real ordering flaw.

Verdict by the AI judge (provisional).

OK. Finished on its own after 26.2 min and produced town.svg.

Bugs

  • bridge deck and wooden jetties overlap confusingly over the river

Scores

AI judge

9.0/10

Draft score — stored total; criterion breakdown unavailable

Visitor votes and reviewer grades are not available yet.

Draft score — stored total; criterion breakdown unavailable. the per-criterion marks could not be read, so the stored score is shown; the displayed total has not been verified through a criterion breakdown.

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. A draft score until the reviewer checks it. Rubric: Wave-1 SVG scoring rubric (AI Model Reviewer).
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

agentic harness (save the file; self-render allowed), 401 characters. Every result for this prompt

Create an isometric SVG town: first design a small sprite sheet of distinct buildings (in <defs>), then place 20+ of them on an isometric grid with roads, trees, a river and a bridge. Pick your own theme and palette. Save it as town.svg in the current directory. You may render and inspect your own output (headless chromium is available at /usr/bin/chromium) and iterate on your own before finishing.

How it was made

Wall time 26m 14sFirst artifact at 7m 46s16 saved versions

Versions saved during the run

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

Version 16 of 16
  1. Version 1 at 7m 45s thumbnailv1 7:45
  2. Version 2 at 13m 56s thumbnailv2 13:56
  3. Version 3 at 16m 08s thumbnailv3 16:08
  4. Version 4 at 17m 19s thumbnailv4 17:19
  5. Version 5 at 18m 41s thumbnailv5 18:41
  6. Version 6 at 19m 42s thumbnailv6 19:42
  7. Version 7 at 20m 14s thumbnailv7 20:14
  8. Version 8 at 20m 25s thumbnailv8 20:25
  9. Version 9 at 21m 17s thumbnailv9 21:17
  10. Version 10 at 22m 08s thumbnailv10 22:08
  11. Version 11 at 22m 40s thumbnailv11 22:40
  12. Version 12 at 23m 01s thumbnailv12 23:01
  13. Version 13 at 23m 43s thumbnailv13 23:43
  14. Version 14 at 23m 54s thumbnailv14 23:54
  15. Version 15 at 25m 16s thumbnailv15 25:16
  16. Version 16 at 25m 27s thumbnailv16 25:27

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

Show all 239 steps

Loading the timeline…

Download the full transcript OpenCode session export, 276 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 $0.23, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $0.45.

Tokens by typeTokens$ per 1MCost
Input (uncached)58,931$0.30$0.0177
Cache write0$0.30$0
Cache read26,815,488$0.01$0.1609
Output69,146$1.20$0.0830
reasoning159,588$1.20$0.1915
Total computed from tokens
$0.4531
Total reported by the harness
$0.2265
Difference
computed 0.2615 vs harness 0.2265

Tokens from OpenCode per-message usage; harness total = sum of OpenCode per-message cost. OpenCode reports reasoning separately; both bill at the output rate (output line here = output only, see reasoning).

Prices: api-docs.deepseek.com/quick_start/pricing (read 2026-09-23); off-peak rates, peak (weekdays 01-04 and 06-10 UTC) is 2x, 2026-09-23.

Run notes

one prompt, neutral harness (OpenCode), self-review allowedwave 1

  • run started in DeepSeek peak hours: 2x rates applied
  • Mode: interactive TUI in tmux (160x48), inside bubblewrap sandbox
  • Isolation: bwrap: private /tmp and /run, private PID ns; only this run dir, harness binaries (ro), opencode config, /usr, /etc bound; HOME/TMPDIR/XDG data private; the project files and other runs not mounted