Ranking weather models by how their forecasts turned out
Details
- External ID
- 49196850
- Source
- HN
- Company
- —
- Product
- Ranking weather models by how their forecasts turned out
- Website domain
- github.io
- Launched
- Aug. 6, 2026
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.40793010752688175
- Tags
- —
- Fetched at
- Sept. 10, 2026, 5:32 a.m.
- Updated at
- Sept. 10, 2026, 5:32 a.m.
Description
Weather apps all claim to be accurate but never show their work. So I built a scoreboard that checks: it takes the forecasts each model published (ECMWF, GFS, ICON, AIFS and others, plus Apple Weather, Foreca, OpenWeather and Visual Crossing), waits for the weather to happen, and scores temperature, wind and rain against observations.A few things that surprised me: - AIFS performs very well, yet almost no commercial apps give you access to it or uses it in their blend (I suspect some do without disclosing it tho) - Foreca scores surprisingly well compared to other apps and raw models - ICON is very accurate around the mediterranean, but performs quite poor everywhere elseThere's also a history page that scores each model back through its full archive (about 5 years for GFS) to see if forecasts have actually gotten better.It's a static page and open-source: https://github.com/NickLeenders/verisky-scoreboard. Public models are scored in your browser against Open-Meteo's archive. Commercial scores come as small aggregates from my server, because those providers' terms don't allow redistributing raw forecasts.It powers an app that does the same per location in more detail, link is on the page.Happy to answer questions about the scoring method.
Enrichment
- Theme
- Vertical
- Energy & climate
- Function
- Analytics & BI
- Audience
- B2B
- AI stance
- Not AI
- Project type
- Commercial product
- Normalized one-liner
- weather model accuracy ranking
- Manually corrected
- False
Could you build this?
Yes Fetching publicly available weather forecasts and historical observations via APIs (like Open-Meteo), storing them in a database, computing error metrics, and displaying a dashboard is standard full-stack development.
Discussion
6 comments analyzed.
Competitors mentioned: ECMWF IFS, GFS, SlickFast, AIFS, AIGFS
Concerns raised: RMSE metric favors average models over AI models despite visual performance differences, AI models produce blurry, low-quality map outputs visually, Model comparison includes non-coverage areas due to ECMWF fill-in approach, Trends tab shows 2021-24 data but only GFS available for those years, Unclear which models actually perform best in specific regions
Feature requests: Expand full model names with descriptions and links, Zoom in on trends tab to focus on relevant data period, Add legend and guidance for data comprehension, Query only region-specific models without ECMWF fallback fill, Use ECMWF IFS 00 and 12 as observations only, not hourly
Competitors
Other products that read as similar to this one — 57 launches clear the similarity bar, closest 8 shown.
Attention rank: #31 of 58 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 246 days after the earliest competitor.
- Weather app to show actual performance of weather models · hn · 2026-05-04 · 5 upvotes · similarity 0.57
- Experiments with Weather Data · hn · 2026-07-29 · 6 upvotes · similarity 0.53
- GrayCloud · hn · 2026-06-04 · 8 upvotes · similarity 0.50
- Sensecast · ph · 2026-09-30 · 2 upvotes · similarity 0.47
- I built a navigation app that displays weather along the route · hn · 2026-04-06 · 55 upvotes · similarity 0.46
- Play or Postpone · ph · 2026-09-11 · 2 upvotes · similarity 0.46
- Brolly, a plain-text weather forecast site · hn · 2026-07-25 · 228 upvotes · similarity 0.45
- Big Weather · ph · 2026-09-26 · 8 upvotes · similarity 0.45
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a analytics & bi tool for Legal yet.