Qwen 3.8 Max in OpenCode 1.18.35
skills on · OpenCode 1.18.35 + skills on (54: 33 video + 21 web/Three.js)Kit: 33 video + 21 web/Three.js · 0 of 54 installed skills used in the session
Zoom, inline player and more ways to view
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.
Wall time 13m 35sCost $1.34 reported
Review
No verdict yet.
The full review
OK. Finished on its own after 13.6 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, 3,863 characters. Every result for this prompt
Build an interactive climate dashboard comparing six weather stations from the exact dataset below (CSV: one row per city and month with the average daily high temperature in Celsius, total rainfall in millimetres and sunshine hours). Embed the data in the page verbatim and compute every number from it; do not invent or alter any value. city,month,avg_high_c,rain_mm,sun_hours Reykjavik,Jan,0.4,77,54 Reykjavik,Feb,0.9,76,81 Reykjavik,Mar,3.8,67,116 Reykjavik,Apr,6.3,48,147 Reykjavik,May,10.1,32,221 Reykjavik,Jun,12.9,24,247 Reykjavik,Jul,13.2,24,274 Reykjavik,Aug,12.2,29,233 Reykjavik,Sep,9.9,37,214 Reykjavik,Oct,6.2,51,160 Reykjavik,Nov,3.1,59,103 Reykjavik,Dec,2.6,74,77 Lisbon,Jan,13.3,100,52 Lisbon,Feb,14.1,99,77 Lisbon,Mar,18.5,69,113 Lisbon,Apr,20.3,47,168 Lisbon,May,25.3,31,222 Lisbon,Jun,27.9,15,245 Lisbon,Jul,28.5,1,259 Lisbon,Aug,27.6,5,259 Lisbon,Sep,24.3,21,212 Lisbon,Oct,21.1,51,146 Lisbon,Nov,18.0,83,100 Lisbon,Dec,15.4,89,84 Singapore,Jan,29.6,254,152 Singapore,Feb,30.6,249,136 Singapore,Mar,30.4,223,151 Singapore,Apr,31.4,201,174 Singapore,May,31.6,183,132 Singapore,Jun,30.9,158,155 Singapore,Jul,31.8,164,167 Singapore,Aug,31.0,163,160 Singapore,Sep,30.8,182,130 Singapore,Oct,31.9,203,172 Singapore,Nov,30.7,235,129 Singapore,Dec,29.9,237,146 Denver,Jan,5.9,47,63 Denver,Feb,7.5,42,76 Denver,Mar,11.6,41,101 Denver,Apr,18.0,40,160 Denver,May,24.9,27,219 Denver,Jun,30.0,23,251 Denver,Jul,30.7,22,253 Denver,Aug,29.4,25,241 Denver,Sep,24.9,38,201 Denver,Oct,17.6,29,153 Denver,Nov,12.2,33,106 Denver,Dec,7.4,35,64 Cape Town,Jan,27.6,9,269 Cape Town,Feb,25.9,16,279 Cape Town,Mar,24.9,30,236 Cape Town,Apr,23.3,60,192 Cape Town,May,21.0,68,142 Cape Town,Jun,18.1,87,111 Cape Town,Jul,17.8,94,111 Cape Town,Aug,18.8,79,131 Cape Town,Sep,20.3,69,163 Cape Town,Oct,22.7,46,187 Cape Town,Nov,24.4,35,227 Cape Town,Dec,25.9,16,280 Mumbai,Jan,30.2,7,62 Mumbai,Feb,30.0,6,68 Mumbai,Mar,29.9,11,121 Mumbai,Apr,32.1,79,166 Mumbai,May,33.0,247,205 Mumbai,Jun,33.0,481,245 Mumbai,Jul,33.2,601,273 Mumbai,Aug,32.3,494,241 Mumbai,Sep,32.5,252,225 Mumbai,Oct,31.5,67,166 Mumbai,Nov,29.8,3,115 Mumbai,Dec,30.1,7,81 The dashboard needs: small-multiple climate charts, one per city, each with monthly temperature as a line over rainfall as bars and the two axes clearly labelled; a radial (polar) chart of the selected city's year with temperature as radius and rainfall as colour; a heatmap of temperature by city and month; KPI cards per city for annual rainfall, hottest and coldest month, temperature range and total sunshine; a 'best month to visit' calculator with sliders for preferred temperature range, maximum rain and minimum sunshine that scores every city-month and lists the top five; a Celsius and Fahrenheit toggle; hover or tap tooltips with exact values; and a short auto-written comparison panel computed from the data. Make it beautiful, editorial and calm, like a data feature in a great magazine. So the page is alive without input, on load the charts draw in and a tour cycles forever: it rotates the radial chart through each city, sweeps a highlight across the heatmap month by month, adjusts the visit calculator sliders to show the ranking change, and toggles units once per loop, until the user touches a control. 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
Versions saved during the run
7 intermediate outputs, in the order the model wrote them.
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 6.5 MB; it is published as a scrubbed, compressed download rather than shown on the page.
Show all 94 steps
Loading the timeline…
Download the full transcript OpenCode session export, 90 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 $1.34, as reported by OpenCode (its own bill for the run).
| Tokens by type | Tokens | $ per 1M | Cost |
|---|---|---|---|
| Input (uncached) | 310,928 | n/a | n/a |
| Cache write | 0 | n/a | n/a |
| Cache read | 1,431,971 | n/a | n/a |
| Output | 60,106 | n/a | n/a |
- Total computed from tokens
- unknown
- Total reported by the harness
- $1.3405
OpenCode 1.18.35 reported its own total; token counts x list prices shown beside it. No list price for qwen3.8-max in config/prices.json; no estimate computed. The harness reports reasoning tokens separately from output; here output includes them (26,400 visible + 33,706 reasoning), and both bill at the output rate.
Run notes
- frozen prompt (written): core requirements sha256 6d5fbb9a4049, full harness prompt sha256 6d5fbb9a4049; exact prompt text used by the existing harness rows of this test on the runs branch (copied from dash_world_weather_stations__claude-code__opus-5-5-high__attempt1/meta.json, sha256 verified); Beta hal
- no TUI: the harness ran in its non-interactive mode, so there are no TUI screenshots; the timelapse is built from version renders only
- OpenCode config (providers only, permission allow-all except question; no agents/instructions) + both default skill kits in xdg/config/opencode/skill (skills=on)
- infra retries: 0
- in the published transcript the sandbox HOME directory is shown as <HOME>
- skills=on: 54 skills installed in the harness skill directory before launch (video-33 remotion-dev/skills + heygen-com/hyperframes@0b5db9da + f; web-threejs-21 [redacted]/ai-AI Model Reviewer skills/ (alpha/mr-homebar)@7521074d98c9).
- Mode: headless run mode (opencode run --format json), inside bubblewrap sandbox
- Isolation audit: none
- Renderer: inline SVG (charts built by the page's own script); no chart library, no canvas, nothing loaded from a CDN (single self-contained file).
- Card video: the run's own video.mp4 (H.264 yuv420p, unchanged). Poster: the run's own render.png.
- Skills on: the run had 54 skills installed (33 video + 21 web/Three.js), as its meta records.
- Qwen 3.8 Max served via Fireworks (OpenCode provider fireworks-ai).
- Same frozen prompt as the other rows on this test; configurations differ and all rows are unscored, so this is not a head-to-head result.







