:root{--bg: #f7f7f5;--paper: #ffffff;--ink: #1f2428;--muted: #6f7477;--line: #deded8;--line-dark: #5d6265;--soft: #efefeb;--accent: #4f78ba;--accent-soft: #e7eef9;--good: #2d7d55;--warn: #b99022;--bad: #bd4b35;--info: #4f78ba;--mono: ui-monospace, SFMono-Regular, Menlo, Consolas, "Liberation Mono", monospace;--sans: Inter, ui-sans-serif, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif}*{box-sizing:border-box}*{scrollbar-width:thin;scrollbar-color:#b8b8b0 transparent}*::-webkit-scrollbar{width:8px;height:8px}*::-webkit-scrollbar-track{background:transparent}*::-webkit-scrollbar-thumb{background:#c6c6bf;border-radius:999px;border:2px solid transparent;background-clip:content-box}*::-webkit-scrollbar-thumb:hover{background:#aaa9a2;border:2px solid transparent;background-clip:content-box}body{margin:0;background:var(--bg);color:var(--ink);font-family:var(--sans)}button,input,select{font:inherit}.app{min-height:100vh}main{overflow:visible}.tag{border:1px solid var(--line-dark);padding:6px 9px;background:#fff;font-size:10px;font-weight:800;letter-spacing:.06em;font-family:var(--mono);text-transform:uppercase}.tag.soft{color:var(--muted);border-color:var(--line)}.content{padding:18px 32px 40px;max-width:1680px;margin:0 auto}.app-header{background:color-mix(in srgb,var(--bg) 96%,#fff);border-bottom:1px solid var(--line)}.header-inner{max-width:1680px;margin:0 auto;padding:12px 32px;display:grid;grid-template-columns:minmax(0,1fr) auto;gap:16px;align-items:center}.brand{border:0;background:transparent;color:inherit;display:flex;align-items:center;gap:10px;min-width:0;padding:0;text-align:left;text-decoration:none;cursor:pointer;transition:opacity .15s ease,transform .15s ease}.brand:hover{opacity:.78;transform:translateY(-1px)}.brand:active{transform:translateY(1px)}.brand-logo{width:42px;height:42px;flex:0 0 auto;display:block;object-fit:contain}.brand-copy{display:flex;align-items:baseline;gap:10px;min-width:0}.brand h1{font-size:clamp(22px,2.2vw,34px);line-height:1;margin:0;letter-spacing:0;white-space:nowrap}.brand-subtitle{color:var(--muted);font-family:var(--mono);font-size:11px;font-weight:800;letter-spacing:.08em;text-transform:uppercase;white-space:nowrap}.run-meta{display:flex;flex-wrap:wrap;gap:8px;align-items:center}.run-actions{display:flex;flex-wrap:wrap;justify-content:flex-end;gap:8px;max-width:640px}.app-footer{max-width:1680px;margin:0 auto;padding:0 32px 28px;color:var(--muted)}.footer-meta{display:flex;flex-wrap:wrap;gap:8px;border-top:1px solid var(--line);padding-top:14px}.metric-band{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:12px;margin:0 0 18px}.metric-card{border:1px solid var(--line);background:var(--paper);padding:14px;min-height:92px}.metric-card b{display:block;font-size:24px;line-height:1;margin-bottom:8px;overflow-wrap:anywhere}.metric-card span{display:block;color:var(--muted);font-family:var(--mono);font-size:10px;font-weight:800;letter-spacing:.08em;text-transform:uppercase}.metric-card small{display:block;margin-top:8px;color:var(--muted);line-height:1.35}h1{font-size:clamp(34px,4vw,58px);line-height:.96;margin:0 0 14px;letter-spacing:0;max-width:1120px}.lede{color:var(--muted);line-height:1.55;max-width:900px;margin:0}.tabs{display:flex;flex-wrap:wrap;gap:8px;margin:0}.tab{border:1px solid var(--line-dark);background:#fff;padding:10px 14px;font-weight:800;cursor:pointer;transition:background .15s ease,color .15s ease,border-color .15s ease,transform .15s ease}.tab:hover{background:#ffffff8a;border-color:#34393b;transform:translateY(-1px)}.tab:active{transform:translateY(1px)}.tab.active{background:var(--ink);color:#fff}.panel{display:none}.panel.active{display:block}html[data-initial-panel=groups] .tab[data-panel=leaderboard].active,html[data-initial-panel=inspect] .tab[data-panel=leaderboard].active{background:#fff;color:var(--ink)}html[data-initial-panel=groups] .tab[data-panel=groups],html[data-initial-panel=inspect] .tab[data-panel=inspect]{background:var(--ink);color:#fff}html[data-initial-panel=groups] #leaderboard.panel.active,html[data-initial-panel=inspect] #leaderboard.panel.active{display:none}html[data-initial-panel=groups] #groups.panel,html[data-initial-panel=inspect] #inspect.panel{display:block}.leaderboard-summary{display:grid;grid-template-columns:repeat(5,minmax(0,1fr));gap:12px;margin:0 0 14px;align-items:stretch}.kpi,.overall-summary,.model-summary{border:1px solid var(--line);background:var(--paper);padding:13px 16px;min-height:86px;display:flex;flex-direction:column;justify-content:flex-start}.overall-summary{border-color:var(--line-dark)}.kpi strong,.overall-summary strong,.model-summary strong{display:block;font-size:34px;line-height:.95;letter-spacing:0;white-space:nowrap}.overall-summary strong{font-size:42px}.kpi span,.overall-summary span,.model-summary>span{display:block;color:var(--muted);font-family:var(--mono);font-size:11px;font-weight:800;letter-spacing:.08em;margin-top:8px;text-transform:uppercase}.kpi small,.overall-summary small,.model-summary small{display:block;margin-top:6px;color:var(--muted);line-height:1.25}.model-summary strong{overflow-wrap:anywhere;white-space:normal}.model-summary .model-secondary,.model-detail{color:var(--ink)}.model-detail b{color:var(--ink);font-family:var(--mono);font-weight:900}.section-grid{display:grid;grid-template-columns:minmax(0,1fr) minmax(0,1fr);gap:16px}.block{border:1px solid var(--line);background:var(--paper);padding:18px;min-width:0}.block h2{margin:0 0 14px;font-size:18px}.block-subhead{margin:20px 0 10px;padding-top:14px;border-top:1px solid var(--line);color:var(--muted);font-family:var(--mono);font-size:11px;font-weight:800;letter-spacing:.08em;text-transform:uppercase}.score-summary{display:grid;grid-template-columns:150px minmax(0,1fr);gap:10px;align-items:stretch}.score-hero{border:1px solid var(--line-dark);background:#fbfbf8;padding:12px;display:flex;flex-direction:column;justify-content:space-between;min-height:112px}.score-hero strong{font-size:42px;line-height:.9;letter-spacing:0}.score-hero span,.score-card span{color:var(--muted);font-family:var(--mono);font-size:10px;font-weight:800;letter-spacing:.08em;text-transform:uppercase}.score-grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:10px}.score-card{border:1px solid var(--line);background:#fff;padding:10px;min-height:58px}.score-card strong{display:block;font-size:22px;line-height:1;margin-bottom:7px;letter-spacing:0}.language-grid{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:10px}.bar-list{display:grid;gap:10px}.bar-row{display:grid;grid-template-columns:minmax(120px,210px) 1fr 70px;align-items:center;gap:10px;font-size:13px}.bar-row b{font-size:12px;font-weight:800;text-align:right}.bar{height:8px;background:var(--soft);border:1px solid color-mix(in srgb,var(--line) 80%,#fff);border-radius:999px;position:relative;overflow:hidden}.bar i{display:block;height:100%;background:var(--info)}.bar.accent i{background:var(--accent)}.toolbar{display:grid;grid-template-columns:minmax(240px,360px) minmax(0,1fr);gap:12px;margin:12px 0;align-items:start}.field{display:grid;gap:5px}.field label,.filter-group label{color:var(--muted);font-family:var(--mono);font-size:12px;font-weight:800;letter-spacing:.08em;text-transform:uppercase}.toolbar input,.toolbar select{border:1px solid var(--line-dark);background:#fff;padding:12px;min-width:0}.filter-panel{display:grid;gap:8px}.filter-group{display:grid;gap:5px}.chip-row{display:flex;flex-wrap:wrap;gap:6px}.filter-chip{border:1px solid var(--line-dark);background:#fff;color:var(--ink);padding:8px 12px;font-family:var(--mono);font-size:12px;font-weight:900;letter-spacing:.04em;cursor:pointer;opacity:.48}.filter-chip.active{opacity:1}.filter-chip.topic.active{border-color:var(--topic-color);color:var(--topic-color);background:color-mix(in srgb,var(--topic-color) 7%,#fff)}.filter-chip.all.active{background:var(--ink);border-color:var(--ink);color:#fff}table{width:100%;border-collapse:collapse;background:var(--paper);border:1px solid var(--line)}th,td{border-bottom:1px solid var(--line);padding:11px 10px;vertical-align:top;text-align:left}th{font-family:var(--mono);font-size:11px;text-transform:uppercase;background:#f1f1ed;position:sticky;top:0;z-index:2;cursor:default}th.sortable{cursor:pointer;user-select:none}th.sortable:hover{background:#e5e5de}td{font-size:13px}.leaderboard-table{table-layout:fixed}.leaderboard-table th:nth-child(1),.leaderboard-table td:nth-child(1){width:56px}.leaderboard-table th:nth-child(n+3),.leaderboard-table td:nth-child(n+3){width:88px;white-space:nowrap;text-align:right}.leaderboard-table th:nth-child(6),.leaderboard-table td:nth-child(6){width:104px}.leaderboard-table th:nth-child(8),.leaderboard-table td:nth-child(8){width:98px}.leaderboard-table th:nth-child(10),.leaderboard-table td:nth-child(10){width:72px}.leaderboard-table th:nth-child(2),.leaderboard-table td:nth-child(2){width:auto}.task-title{font-weight:800;line-height:1.3}.subtle{color:var(--muted);font-family:var(--mono);font-size:11px}.click-row{cursor:pointer}.click-row:hover{background:#eeeeea}.metric-value{display:inline-flex;align-items:baseline;justify-content:flex-end;min-width:58px;padding:0;font-family:var(--mono);font-weight:900;color:color-mix(in srgb,var(--metric-color, var(--ink)) 82%,#111)}.metric-value.small{min-width:0}.topic-chip{display:inline-flex;align-items:center;font-family:var(--mono);font-size:11px;line-height:1.2;padding:3px 7px;border:1px solid color-mix(in srgb,var(--topic-color) 80%,#000);background:var(--topic-color);color:var(--topic-ink);font-weight:800}.plain-metric{font-family:var(--mono);font-weight:800;color:var(--ink)}.task-stack{display:grid;gap:6px;max-width:none}.task-context{display:flex;flex-wrap:wrap;gap:8px;align-items:baseline}.language-text{color:var(--muted);font-family:var(--mono);font-size:11px;font-weight:800}.detail{display:grid;grid-template-columns:minmax(280px,340px) minmax(0,1fr) minmax(320px,380px);grid-template-areas:"list head side" "list report side";gap:16px;align-items:start}.detail.report-focus{grid-template-columns:minmax(190px,240px) minmax(0,1fr);grid-template-areas:"toc head" "toc report"}.report-focus .task-list,.report-focus .report-side{display:none}.task-list{grid-area:list;border:1px solid var(--line);background:var(--paper);max-height:calc(100vh - 32px);overflow:auto;position:sticky;top:16px}.task-list-search{position:sticky;top:0;z-index:3;background:var(--paper);border-bottom:1px solid var(--line);padding:10px}.task-list-search input{width:100%;border:1px solid var(--line-dark);background:#fff;padding:10px;min-width:0}.task-button{width:100%;border:0;border-bottom:1px solid var(--line);background:transparent;text-align:left;padding:12px 13px;cursor:pointer;display:grid;gap:6px;transition:background .15s ease,transform .15s ease,color .15s ease}.task-button.active,.task-button:hover{background:#eeeeea}.task-button:hover{transform:translate(2px)}.task-button:active{transform:translate(0)}.task-button .task-title{color:#3f4548;font-size:13px}.task-button .task-meta{display:block;line-height:1.35}.task-topic-text{color:color-mix(in srgb,var(--topic-color) 86%,#111);font-weight:950;font-size:13px}.task-score-text{color:var(--score-color);font-weight:900}.detail-pane{min-width:0;display:grid;gap:16px}.report-main{grid-area:report;min-width:0;display:grid;gap:12px}.report-switching .report-main>.block{animation:report-enter .22s ease both}@keyframes report-enter{0%{opacity:.35;transform:translateY(10px)}to{opacity:1;transform:translateY(0)}}.report-side{grid-area:side;min-width:0;display:grid;gap:12px;position:sticky;top:16px;max-height:calc(100vh - 32px);overflow:auto}.report-toc{display:none;grid-area:toc}.report-focus .report-toc{display:block;position:sticky;top:16px;max-height:calc(100vh - 32px);overflow:auto;border:1px solid var(--line);background:color-mix(in srgb,var(--paper) 88%,var(--soft));padding:14px}.report-toc h2{margin:0 0 12px;color:var(--muted);font-family:var(--mono);font-size:11px;font-weight:900;letter-spacing:.08em;text-transform:uppercase}.report-toc nav{display:grid;gap:4px}.toc-link{border-left:2px solid transparent;color:#4f5558;display:block;font-size:12px;line-height:1.25;padding:7px 8px;text-decoration:none;transition:background .15s ease,color .15s ease,border-color .15s ease,transform .15s ease}.toc-link:hover{background:#fff9;border-color:#73787a;color:var(--ink);transform:translate(2px)}.toc-link.h3{color:var(--muted);font-size:11px;padding-left:18px}.toc-empty{color:var(--muted);font-size:12px;line-height:1.35}.detail-head{grid-area:head}.report-focus .detail-head,.report-focus .report-main{max-width:1240px;width:100%;margin:0 auto}.report-toolbar{display:flex;justify-content:space-between;gap:12px;align-items:start}.report-toolbar h2{margin:0;font-size:18px}.report-actions{display:flex;flex-wrap:wrap;gap:8px;justify-content:flex-end}.small-button{border:1px solid var(--line-dark);background:#fff;padding:8px 10px;font-size:11px;font-family:var(--mono);font-weight:900;letter-spacing:.04em;text-transform:uppercase;cursor:pointer;transition:background .15s ease,color .15s ease,border-color .15s ease,transform .15s ease}.small-button:hover{background:#ffffff8a;border-color:#34393b;transform:translateY(-1px)}.small-button:active{transform:translateY(1px)}.report-top-button{position:fixed;right:auto;bottom:24px;z-index:30;display:inline-flex;align-items:center;gap:8px;border:1px solid #73787a;background:#f5f5f2e6;color:#34393b;padding:8px 12px;font-family:var(--mono);font-size:12px;font-weight:900;letter-spacing:.04em;text-transform:uppercase;cursor:pointer;opacity:0;pointer-events:none;transform:translateY(8px);transition:opacity .15s ease,transform .15s ease,background .15s ease,color .15s ease,border-color .15s ease;backdrop-filter:blur(4px)}.report-top-button.visible{opacity:1;pointer-events:auto;transform:translateY(0)}.report-top-button:hover{background:#ffffff8a;color:#1f2428;border-color:#34393b}.report-top-button:active{transform:translateY(2px)}.report-top-icon{font-size:26px;line-height:.72}.report-side .bar-row{grid-template-columns:minmax(120px,1fr) 96px 54px;gap:8px}.diagnostic-card{border:1px solid var(--line);background:var(--paper);padding:16px;display:grid;gap:12px}.diagnostic-card h2{margin:0;font-size:16px;line-height:1.2}.overall-card{border-color:color-mix(in srgb,var(--score-color, var(--line-dark)) 55%,var(--line));background:linear-gradient(180deg,color-mix(in srgb,var(--score-color, #fff) 9%,#fff),#fff 58%)}.overall-label{display:block;color:var(--muted);font-size:13px;font-weight:800;line-height:1}.overall-score{display:flex;align-items:baseline;gap:7px;color:color-mix(in srgb,var(--score-color, var(--ink)) 82%,#111)}.overall-score strong{font-size:58px;line-height:.92;letter-spacing:0}.hero-meta{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));gap:10px;border-top:1px solid var(--line);padding-top:12px}.hero-meta span,.summary-row span,.token-subline span{color:var(--muted);font-size:12px}.hero-meta b,.summary-row b,.token-subline b{color:var(--ink);font-size:13px}.summary-list{display:grid;gap:8px}.summary-row{display:grid;grid-template-columns:92px minmax(0,1fr);gap:10px;align-items:baseline}.summary-row b{justify-self:end;text-align:right}.token-subline{display:flex;flex-wrap:wrap;gap:10px;padding-top:2px;color:var(--muted);font-size:12px}.usage-block{border-top:1px solid var(--line);padding-top:12px;display:grid;gap:8px}.usage-line{display:flex;justify-content:space-between;gap:12px;align-items:baseline}.usage-line span,.usage-breakdown span{color:var(--muted);font-size:12px}.usage-line b{font-size:18px;line-height:1}.usage-breakdown{display:flex;flex-wrap:wrap;gap:8px 14px}.usage-breakdown b{color:var(--ink);font-size:12px}.source-card header{display:flex;justify-content:space-between;gap:12px;align-items:baseline}.source-card header span{color:var(--muted);font-size:12px;text-align:right}.source-bar{height:12px;background:var(--soft);border:1px solid color-mix(in srgb,var(--line) 80%,#fff);border-radius:999px;overflow:hidden;display:flex}.source-segment{height:100%;position:relative;flex:0 0 auto;background:var(--source-soft)}.source-segment+.source-segment{border-left:1px solid rgba(255,255,255,.8)}.source-used{position:absolute;inset:0 auto 0 0;background:var(--source-strong)}.source-legend{display:grid;gap:7px}.source-row{display:grid;grid-template-columns:minmax(70px,1fr) auto;gap:8px;align-items:baseline;font-size:12px}.source-row>span{color:var(--source-strong);text-decoration:underline;text-decoration-color:var(--source-strong);text-underline-offset:3px;font-weight:800}.source-row b span{text-decoration:none}.source-row .source-used-text{color:var(--source-strong)}.source-row .source-retrieved-text{color:color-mix(in srgb,var(--source-soft) 58%,var(--source-strong))}.phase-row{display:grid;grid-template-columns:minmax(110px,1fr) 40px 56px;gap:8px;align-items:center;font-size:13px}.phase-row b{font-size:12px;font-weight:800;text-align:right}.phase-row span:first-child{overflow-wrap:anywhere}.phase-row .bar{height:10px;grid-column:1 / -1}.rubric-disclosure{border:1px solid var(--line);background:var(--paper)}.rubric-disclosure summary{cursor:pointer;padding:14px 16px;font-size:16px;font-weight:800;list-style:none}.rubric-disclosure summary::-webkit-details-marker{display:none}.rubric-disclosure summary:after{content:"+";float:right;color:var(--muted)}.rubric-disclosure[open] summary{border-bottom:1px solid var(--line)}.rubric-disclosure[open] summary:after{content:"-"}.rubric-content{display:grid;gap:14px;padding:16px}.rubric-content h2{margin:0 0 10px;font-size:15px;line-height:1.2}.detail-head .tag{display:inline-block;margin-bottom:10px}.detail-head h2{margin:0 0 10px;line-height:1.15;overflow-wrap:anywhere}.task-prompt{margin:0;color:var(--ink);line-height:1.55;max-width:1000px;white-space:pre-wrap}.two-col{display:grid;grid-template-columns:1fr 1fr;gap:16px}.groups-layout{display:grid;grid-template-columns:minmax(0,1fr) minmax(0,1fr);gap:16px;align-items:start}.group-stack{display:grid;gap:16px}.article{overflow:visible;line-height:1.55;font-size:17px;padding:4px 0 24px}.report-focus .article{max-width:1100px;margin:0 auto;font-size:18px}.article h1,.article h2,.article h3{line-height:1.15;margin:.95em 0 .4em}.article h1{font-size:34px}.article h2{font-size:25px}.article h3{font-size:19px}.article p{margin:.65em 0}.article ul,.article ol{margin:.5em 0 .8em;padding-left:1.35em}.article li{margin:.25em 0}.article p,.article li{max-width:92ch}.article hr{border:0;border-top:1px solid var(--line);margin:1.1em 0}.article code{background:#f3f3ef;border:1px solid var(--line);padding:1px 4px;font-family:var(--mono);font-size:.92em}.article pre{white-space:pre-wrap;background:#f3f3ef;padding:12px;border:1px solid var(--line);overflow:auto}.article pre code{border:0;padding:0;background:transparent}.article a{color:#2458d3;text-decoration-thickness:1px;text-underline-offset:2px}.article .source-ref{display:grid;grid-template-columns:max-content minmax(0,1fr);gap:8px;margin:.35em 0;max-width:96ch}.article .source-ref span{font-family:var(--mono);font-weight:800}.article table{font-size:13px;margin:12px 0}.criteria-list{display:grid;gap:10px;max-height:48vh;overflow:auto}.criterion{border:1px solid var(--line);padding:11px;background:#fff}.criterion b{display:block;font-size:13px;margin-bottom:4px}.criterion p{margin:0;color:var(--muted);font-size:12px;line-height:1.45}.empty{border:1px dashed var(--line);padding:24px;color:var(--muted);background:#fff}@media(max-width:1100px){.header-inner,.section-grid,.detail,.two-col,.groups-layout{grid-template-columns:1fr}.run-actions{justify-content:flex-start;max-width:none}.metric-band{grid-template-columns:repeat(2,1fr)}.score-summary{grid-template-columns:1fr}.leaderboard-summary{grid-template-columns:repeat(2,1fr)}.toolbar{grid-template-columns:1fr}.detail,.detail.report-focus{grid-template-columns:1fr;grid-template-areas:none}.task-list,.report-side,.report-toc,.detail-head,.report-main{position:static;max-height:none;grid-area:auto}.report-focus .report-toc{position:static;max-height:none}th{top:0}}@media(max-width:640px){.content,.header-inner,.app-footer{padding-left:14px;padding-right:14px}.brand{gap:8px}.brand-logo{width:36px;height:36px}.brand-copy{display:grid;gap:4px}.brand h1{white-space:normal}.leaderboard-summary,.toolbar,.score-grid,.language-grid,.metric-band{grid-template-columns:1fr}.bar-row{grid-template-columns:minmax(0,1fr) 1fr 58px;gap:8px}h1{font-size:34px}.report-top-button{right:14px;bottom:14px;padding:7px 9px}}
