AI Model Reviewer

DeepSeek V4.1 Flash in OpenCode 1.18.32

skills off

← Open in the gallerySame prompt, all models

Zoom, inline player and more ways to view
Snapshot 1 of 1 saved during DeepSeek V4.1 Flash's run
Still snapshots saved during the run (no motion recording): 1 distinct frame.

Live page incomplete: it loads vendor/three.module.js, which the run never published, so it is not played here. The model's own file is published as it was left: open it (on the separate demo site).

OKEiffelmax effortNeutral harness

Wall time 28m 46sCost $0.10 reported

Review

No verdict yet.

The full review

OK. Finished on its own after 28.8 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, 416 characters. Every result for this prompt

Build the Eiffel Tower in Three.js. 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 28m 46sFirst artifact at 3m 49s29 saved versions

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 152 steps

Loading the timeline…

Download the full transcript OpenCode session export, 663 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 $0.10, as reported by OpenCode (its own bill for the run). The list-price estimate from the token counts is $0.10.

Tokens by typeTokens$ per 1MCost
Input (uncached)39,543$0.15$0.0059
Cache write0$0.15$0
Cache read9,860,608$0.00$0.0296
Output112,926$0.60$0.0678
of which reasoning84,636billed as output
Total computed from tokens
$0.1033
Total reported by the harness
$0.1033
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 (28,290 visible + 84,636 reasoning), and both bill at the output rate.

Prices: https://api-docs.deepseek.com/quick_start/pricing, 2026-09-24.

Run notes

one prompt, agentic harness (self-review allowed)reconstructed prompt

  • frozen prompt (reconstructed): recovery/prompts_recovered/threejs_eiffel.assembled_candidate.txt: verbatim ask + recorded harness suffix
  • 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: none