Detailed README, meta description, structured data

index.html

@@ -1,5 +1,9 @@
 <!doctype html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1">
-<title>Global Weather Model Leaderboard</title>
+<title>Global Weather Model Leaderboard: which weather model is most accurate?</title>
+<meta name="description" content="Daily accuracy ranking of global weather forecast models, AI and physics: Darwin-Prediction-Weather, ECMWF AIFS, ECMWF IFS, GFS, AIGFS, ICON, JMA, GEM and MET Norway, scored against ERA5 for 24 world cities since 2026-01-01, with a 10-day outlook.">
+<meta property="og:title" content="Global Weather Model Leaderboard"><meta property="og:description" content="Daily accuracy ranking of global weather forecast models, AI and physics: Darwin-Prediction-Weather, ECMWF AIFS, ECMWF IFS, GFS, AIGFS, ICON, JMA, GEM and MET Norway, scored against ERA5 for 24 world cities since 2026-01-01, with a 10-day outlook."><meta property="og:type" content="website"><meta property="og:url" content="https://huggingface.co/spaces/FINAL-Bench/Weather-Model-Leaderboard">
+<link rel="canonical" href="https://huggingface.co/spaces/FINAL-Bench/Weather-Model-Leaderboard">
+<script type="application/ld+json">{"@context":"https://schema.org","@graph":[{"@type":"WebApplication","name":"Global Weather Model Leaderboard","url":"https://huggingface.co/spaces/FINAL-Bench/Weather-Model-Leaderboard","applicationCategory":"Weather","description":"Daily accuracy ranking of global weather forecast models, AI and physics: Darwin-Prediction-Weather, ECMWF AIFS, ECMWF IFS, GFS, AIGFS, ICON, JMA, GEM and MET Norway, scored against ERA5 for 24 world cities since 2026-01-01, with a 10-day outlook.","creator":{"@type":"Organization","name":"VIDRAFT","email":"vidraft@mail.vidraft.net"},"license":"https://creativecommons.org/licenses/by-nc/4.0/"},{"@type":"Dataset","name":"Weather Model Forecast Archive 2026","url":"https://huggingface.co/datasets/FINAL-Bench/Weather-Model-Forecast-Archive","description":"Daily forecasts of global weather models and ERA5 observed daily maximum temperature for 24 cities since 2026-01-01.","creator":{"@type":"Organization","name":"VIDRAFT"},"license":"https://creativecommons.org/licenses/by-nc/4.0/"},{"@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Which weather model is the most accurate in 2026?","acceptedAnswer":{"@type":"Answer","text":"For daily maximum temperature across 24 world cities, Darwin-Prediction-Weather has the lowest error at every lead from 1 to 7 days. Among weather-centre models, ECMWF AIFS ranks first."}},{"@type":"Question","name":"Are AI weather models more accurate than physics models?","acceptedAnswer":{"@type":"Answer","text":"In this record ECMWF AIFS (AI) has lower error than ECMWF IFS (physics) at every lead, and NOAA AIGFS (AI) has lower error than NOAA GFS (physics) at every lead."}},{"@type":"Question","name":"How often is the leaderboard updated?","acceptedAnswer":{"@type":"Answer","text":"Once a day: new forecasts are archived, newly published observations are scored, and the cumulative record and the 10-day outlook are refreshed."}}]}]}</script>
 <style>
 :root{--bg:#061226;--panel:#0d2247;--panel2:#11305f;--line:#1d3f78;--ink:#f2f7ff;--mut:#9db4d8;--cy:#35d0ff;--gold:#ffc83d;--red:#ff4d5e;--ai:#35d0ff;--ph:#b9c7e0}
 *{box-sizing:border-box}html{background:var(--bg)}
@@ -44,6 +48,7 @@ svg{width:100%;height:auto;display:block}.lg{display:flex;flex-wrap:wrap;gap:6px
 <div class="top"><span class="live"><i></i>LIVE</span><span class="brand">Global Weather Model <b>Leaderboard</b></span><span class="stamp" id="stamp">Loading…</span></div>
 <div class="tick"><span id="tick">Loading the latest verification…</span></div>
 <main>
+<noscript><h1>Global Weather Model Leaderboard</h1><p>Daily accuracy ranking of global weather forecast models, AI and physics: Darwin-Prediction-Weather, ECMWF AIFS, ECMWF IFS, GFS, AIGFS, ICON, JMA, GEM and MET Norway, scored against ERA5 for 24 world cities since 2026-01-01, with a 10-day outlook. 2026 year to date, RMSE of daily maximum temperature in °C at 1, 3, 5 and 7 days ahead: Darwin-Prediction-Weather (VIDRAFT, AI) 0.84, 1.17, 1.59, 2.09. ECMWF AIFS (AI) 1.35, 1.59, 1.90, 2.42. ECMWF IFS (Physics) 1.44, 1.77, 2.21, 2.85. Data: <a href="https://huggingface.co/datasets/FINAL-Bench/Weather-Model-Forecast-Archive">Weather-Model-Forecast-Archive</a>. Contact: vidraft@mail.vidraft.net</p></noscript>
 <div class="ctl">
 <label>Forecast lead<select id="lead"></select></label>
 <label>Period<select id="period"><option value="day">Single day</option><option value="7">Last 7 days</option><option value="14">Last 14 days</option><option value="30">Last 30 days</option><option value="90">Last 90 days</option><option value="ytd" selected>2026 year to date</option></select></label>