diff --git "a/eval/reports.html" "b/eval/reports.html" --- "a/eval/reports.html" +++ "b/eval/reports.html" @@ -81,12 +81,12 @@ code { background:#eef1f5; padding:1px 5px; border-radius:4px; font-size:12px; }
Overall score is the unweighted mean of Prompt Fit and the six rubric dimensions, following DesignEvaluator V5.9.2.
-| model | base | optimizer | global batch | step | HF subfolder |
|---|---|---|---|---|---|
| 27B AdamW step400 | Qwen3.8-27B | AdamW | 128 | 400 | designcoder_qwen3.8_27b_adamw_bs128_data41287_step400 |
| 9B AdamW step200 | Qwen3.5-9B | AdamW | 256 | 200 | designcoder_qwen3.5_9b_adamw_bs256_data41287_step200 |
| 4B AdamW step200 | Qwen3.5-4B | AdamW | 256 | 200 | designcoder_qwen3.5_4b_adamw_bs256_data41287_step200 |
| 4B Muon step200 | Qwen3.5-4B | Muon | 256 | 200 | designcoder_qwen3.5_4b_muon_bs256_data41287_step200 |
| model | n | mean | median | p25 | min | max | stdev | prompt fit | rubric % | <60 | render fail |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 27B AdamW step400 | 200 | 87.89 | 88.93 | 82.86 | 46.43 | 100.00 | 9.52 | 84.10 | 88.60 | 2 | 0 |
| 9B AdamW step200 | 200 | 84.40 | 85.59 | 79.29 | 38.57 | 100.00 | 10.43 | 78.35 | 85.37 | 6 | 1 |
| 4B AdamW step200 | 200 | 82.12 | 84.41 | 74.05 | 38.33 | 100.00 | 12.46 | 75.25 | 83.24 | 14 | 1 |
| 4B Muon step200 | 200 | 77.62 | 80.83 | 70.75 | 35.08 | 100.00 | 13.73 | 64.60 | 79.43 | 22 | 3 |
| model | n | mean | median | p25 | min | max | stdev | prompt fit | rubric % | <60 | render fail |
| 27B AdamW step400 | 200 | 87.04 | 89.20 | 82.22 | 13.09 | 100.00 | 10.92 | 84.10 | 88.60 | 4 | 0 |
| 9B AdamW step200 | 200 | 82.14 | 84.69 | 74.90 | 45.35 | 100.00 | 11.99 | 78.35 | 85.37 | 11 | 1 |
| 4B AdamW step200 | 200 | 80.06 | 82.82 | 71.28 | 38.59 | 100.00 | 13.47 | 75.25 | 83.24 | 23 | 1 |
| 4B Muon step200 | 200 | 71.34 | 73.77 | 60.51 | 29.13 | 97.18 | 15.34 | 64.60 | 79.43 | 48 | 3 |
p25 = 25th percentile; a high mean with a low p25 means the model is inconsistent rather than uniformly good.
@@ -104,9 +104,9 @@ code { background:#eef1f5; padding:1px 5px; border-radius:4px; font-size:12px; }The benchmark requires Track A/B and landing/dashboard to be reported separately.
-Share of cases (%) falling in each score band.
-| score | group | case_id | judge summary |
|---|---|---|---|
| 46.43 | A/dashboard | dashboard-045-streaming-dashboard-obs | A polished dark console shell is visible, but most core storm-tracking visualizations and table content are blank. |
| 50.95 | A/landing | landing-027-art-deco | A polished Art Deco landing page with strong atmosphere and booking emphasis is materially weakened by the absent timetable, non-symmetrical hero imagery, and incomplete offering grids. |
| 61.55 | A/dashboard | dashboard-002-armin-hofmann-contrast-and-reduction | The dashboard has a strong monochrome structural shell, but its empty charts, ticket table, station rail, and inspector make the operational experience incomplete. |
| 66.67 | A/dashboard | dashboard-005-dieter-rams-silent-control-panel | A polished and highly legible silent-control dashboard whose default overview is strong, but the screenshot does not demonstrate the selected-lift inspector, capacity consequence, webcam, maintenance, loading, or active |
| 68.10 | A/landing | landing-015-biomorphic-design | The page is polished and atmospherically cohesive with complete downstream sections and reservation flow, but the missing hero selector, absent table-lamp clarity, and occluded compact-card copy weaken fidelity and usabi |
| 68.10 | A/landing | landing-041-stop-motion-craft | A polished, cohesive pottery-drop landing page communicates the collection and reservation flow well, but several specific handmade and overhead-photography requirements are visibly absent. |
| 68.88 | B/dashboard | track-b-dashboard-016-src-393 | The dashboard strongly prioritizes and explains the funding shortfall in a polished dense layout, but the visible workflow stops before intercompany staging, approval, rationale, and resolved-state closure. |
| 68.97 | A/dashboard | dashboard-020-data-storytelling-ui | A polished and well-structured Gateflow shell presents strong KPIs and controls, but its blank chart, heatmap, and flight table prevent complete operational monitoring. |
| 69.39 | B/landing | track-b-landing-001-src-268 | The page has a polished, calm booking-oriented structure, but incomplete room presentation, a broken image and visibly unrelated photography materially weaken the brief fit. |
| 69.76 | A/landing | landing-110-blackout-xerox-punk | A polished and highly coherent Xerox-punk race landing page covers most content and commerce needs, but lacks several required visual asset types and does not visibly demonstrate populated race-card states. |
| 69.93 | B/dashboard | track-b-dashboard-001-src-368 | A polished, decision-ready cold-chain dashboard with strong prioritization and evidence, weakened mainly by the missing corrective-action control and limited trailer/depot detail. |
| 70.48 | A/dashboard | dashboard-009-arcade-cabinet-ops | A polished and highly legible arcade race-control dashboard is substantially complete, but its obscured leaderboard and missing visible row-to-inspector anchor are major localized weaknesses. |
| 70.71 | A/dashboard | dashboard-016-financial-broadsheet | A polished and decision-ready opening-weekend broadsheet that strongly covers the core workflow, while missing authentic poster thumbnails, correspondent margin notes, restruck estimates, and serif index numerals. |
| 70.71 | A/dashboard | dashboard-029-lime-noir-logistics-glass | A polished and decision-ready lime-noir turnover dashboard is shown, but explicit RoomRelay branding, table scrolling, empty-state coverage, and the selected-room inspector flow are absent. |
| 72.38 | A/dashboard | dashboard-041-scada-hmi-industrial | A strong SCADA-style monitoring console with comprehensive visible data and actions, held back by overlapping panels, misplaced charts, and missing acknowledgement identity and TRIP evidence. |
| 13.09 | A/dashboard | dashboard-045-streaming-dashboard-obs | |
| 45.65 | A/dashboard | dashboard-002-armin-hofmann-contrast-and-reduction | |
| 55.79 | A/dashboard | dashboard-006-carbon-fiber-telemetry | |
| 59.81 | A/dashboard | dashboard-009-arcade-cabinet-ops | |
| 62.65 | A/landing | landing-005-april-greiman-digital-collage | |
| 65.42 | A/dashboard | dashboard-020-data-storytelling-ui | |
| 65.78 | B/dashboard | track-b-dashboard-026-src-410 | |
| 67.25 | A/dashboard | dashboard-003-blueprint-hologram-console | |
| 67.63 | A/landing | landing-083-legal-authority | |
| 68.08 | A/landing | landing-019-paul-rand-modernist-wit | |
| 69.30 | A/landing | landing-100-dada-collage | |
| 69.81 | A/landing | landing-060-dieter-rams-silent-control-panel | |
| 71.05 | A/dashboard | dashboard-036-obsidian-aura-portfolio | |
| 71.53 | A/landing | landing-061-pop-art | |
| 71.97 | A/landing | landing-037-constructivism |
| case_id | track | surface | 27B AdamW step400 | 9B AdamW step200 | 4B AdamW step200 | 4B Muon step200 |
|---|---|---|---|---|---|---|
| dashboard-002-armin-hofmann-contrast-and-reduction | A | dashboard | 61.55 | 87.02 | 78.81 | 64.64 |
| dashboard-003-blueprint-hologram-console | A | dashboard | 82.27 | 80.84 | 90.00 | 72.27 |
| dashboard-004-dashboard-brutalism | A | dashboard | 100.00 | 90.95 | 86.87 | 85.44 |
| dashboard-005-dieter-rams-silent-control-panel | A | dashboard | 66.67 | 71.43 | 84.29 | 49.52 |
| dashboard-006-carbon-fiber-telemetry | A | dashboard | 73.04 | 93.57 | 86.43 | 86.23 |
| dashboard-007-ceramic-bento-metrics | A | dashboard | 76.83 | 54.52 | 59.37 | 81.83 |
| dashboard-008-admin-crud-panel | A | dashboard | 84.52 | 38.57 | 72.62 | 58.33 |
| dashboard-009-arcade-cabinet-ops | A | dashboard | 70.48 | 77.14 | 44.76 | 62.38 |
| dashboard-011-anime-dashboard | A | dashboard | 96.43 | 83.81 | 78.21 | 59.64 |
| dashboard-012-glass-cockpit-avionics | A | dashboard | 93.57 | 93.93 | 65.18 | 44.88 |
| dashboard-013-bauhaus | A | dashboard | 93.33 | 79.05 | 97.62 | 73.33 |
| dashboard-014-developer-first-minimal | A | dashboard | 90.95 | 89.52 | 90.95 | 68.01 |
| dashboard-015-ev-instrument-cluster | A | dashboard | 93.57 | 78.81 | 63.33 | 60.00 |
| dashboard-016-financial-broadsheet | A | dashboard | 70.71 | 74.64 | 69.64 | 71.67 |
| dashboard-018-crypto-dashboard | A | dashboard | 90.24 | 61.90 | 38.33 | 86.43 |
| dashboard-019-executive-kpi-dashboard | A | dashboard | 97.38 | 83.81 | 84.76 | 86.19 |
| dashboard-020-data-storytelling-ui | A | dashboard | 68.97 | 60.40 | 82.54 | 52.06 |
| dashboard-021-fluent-design | A | dashboard | 78.10 | 76.67 | 65.68 | 44.52 |
| dashboard-023-adaptive-ambient-ui | A | dashboard | 87.02 | 83.45 | 78.21 | 83.93 |
| dashboard-024-honeycomb-paper-ledger | A | dashboard | 86.19 | 83.81 | 88.57 | 78.10 |
| dashboard-027-kenya-hara-white-and-emptiness | A | dashboard | 91.02 | 97.14 | 92.24 | 78.37 |
| dashboard-029-lime-noir-logistics-glass | A | dashboard | 70.71 | 90.95 | 66.90 | 72.62 |
| dashboard-030-lucky-swaps-volumetric-console | A | dashboard | 82.86 | 77.86 | 79.05 | 84.76 |
| dashboard-031-mac-os-aqua-nostalgia | A | dashboard | 98.57 | 74.69 | 78.98 | 65.17 |
| dashboard-032-massimo-vignelli-typographic-discipline | A | dashboard | 94.42 | 89.52 | 92.99 | 84.89 |
| dashboard-033-motorsport-pit-wall | A | dashboard | 86.69 | 67.30 | 66.80 | 77.38 |
| dashboard-035-observability-dark | A | dashboard | 91.67 | 87.38 | 83.81 | 85.79 |
| dashboard-036-obsidian-aura-portfolio | A | dashboard | 89.57 | 81.71 | 58.16 | 72.77 |
| dashboard-037-pale-grid-node-console | A | dashboard | 90.00 | 88.70 | 74.05 | 56.47 |
| dashboard-039-retro-lcd-control-panel | A | dashboard | 87.94 | 82.22 | 76.98 | 81.11 |
| dashboard-040-rpg-guild-operations | A | dashboard | 88.10 | 86.67 | 92.86 | 91.76 |
| dashboard-041-scada-hmi-industrial | A | dashboard | 72.38 | 69.05 | 74.52 | 55.48 |
| dashboard-042-soft-rubber-control-room | A | dashboard | 96.19 | 96.19 | 89.76 | 77.14 |
| dashboard-043-split-flap-departure-board | A | dashboard | 94.29 | 58.53 | 70.74 | 42.81 |
| dashboard-044-sticker-sheet-analytics | A | dashboard | 91.43 | 88.57 | 82.86 | 81.43 |
| dashboard-045-streaming-dashboard-obs | A | dashboard | 46.43 | 92.14 | 84.52 | 38.09 |
| dashboard-046-studded-brick-ops | A | dashboard | 87.78 | 68.17 | 96.98 | 61.98 |
| dashboard-047-susan-kare-pixel-icon-clarity | A | dashboard | 76.34 | 75.76 | 63.98 | 42.66 |
| dashboard-048-teenage-engineering-industrial | A | dashboard | 85.24 | 74.76 | 73.33 | 69.76 |
| dashboard-049-topographic-terrain-console | A | dashboard | 99.11 | 91.07 | 58.81 | 70.42 |
| landing-001-1970s-documentary | A | landing | 90.24 | 80.48 | 87.62 | 82.62 |
| landing-002-afrofuturism | A | landing | 84.05 | 79.29 | 74.52 | 74.52 |
| landing-003-1980s-arcade-cinema | A | landing | 94.29 | 100.00 | 82.86 | 72.86 |
| landing-004-70s-warm-retro | A | landing | 87.86 | 85.71 | 97.14 | 85.71 |
| landing-005-april-greiman-digital-collage | A | landing | 87.86 | 90.24 | 90.00 | 90.24 |
| landing-006-acid-graphics | A | landing | 90.24 | 80.71 | 90.24 | 73.33 |
| landing-007-a24-indie-editorial | A | landing | 85.48 | 83.10 | 96.43 | 96.43 |
| landing-008-abstract-expressionism | A | landing | 83.33 | 85.24 | 87.14 | 58.10 |
| landing-009-adaptive-ambient-ui | A | landing | 97.14 | 77.86 | 74.86 | 72.96 |
| landing-011-80s-synthwave | A | landing | 86.67 | 79.39 | 79.52 | 68.91 |
| landing-012-academia | A | landing | 91.67 | 96.43 | 92.86 | 93.57 |
| landing-013-bohemian | A | landing | 100.00 | 85.00 | 95.00 | 100.00 |
| landing-015-biomorphic-design | A | landing | 68.10 | 83.10 | 87.38 | 73.33 |
| landing-016-de-stijl | A | landing | 96.43 | 75.48 | 91.19 | 98.57 |
| landing-017-anodized-metal | A | landing | 87.62 | 84.29 | 78.10 | 84.29 |
| landing-018-indie-sleaze-2005 | A | landing | 98.57 | 81.07 | 100.00 | 85.00 |
| landing-019-paul-rand-modernist-wit | A | landing | 80.00 | 85.71 | 78.41 | 70.64 |
| landing-020-arc-browser-like-playful-productivity | A | landing | 95.97 | 97.27 | 93.12 | 85.52 |
| landing-023-coastal-grandmother | A | landing | 92.86 | 85.00 | 91.43 | 80.00 |
| landing-025-bauhaus | A | landing | 88.81 | 79.29 | 80.58 | 74.29 |
| landing-026-carbon-fiber | A | landing | 76.19 | 92.86 | 70.00 | 80.95 |
| landing-027-art-deco | A | landing | 50.95 | 92.86 | 65.00 | 67.38 |
| landing-028-christopher-nolan-esque | A | landing | 85.00 | 82.14 | 87.14 | 88.57 |
| landing-029-aurora-mesh | A | landing | 96.43 | 82.38 | 98.57 | 88.57 |
| landing-031-kubrick-symmetry | A | landing | 81.67 | 95.24 | 95.24 | 81.67 |
| landing-032-scandinavian-minimal | A | landing | 97.96 | 97.96 | 91.77 | 97.96 |
| landing-033-underground-brutalism | A | landing | 87.38 | 90.40 | 90.56 | 81.35 |
| landing-034-brushed-aluminum | A | landing | 95.00 | 83.69 | 91.67 | 92.38 |
| landing-035-linen-texture | A | landing | 80.24 | 78.20 | 86.43 | 84.52 |
| landing-036-energy-utility | A | landing | 100.00 | 93.81 | 96.43 | 80.48 |
| landing-037-constructivism | A | landing | 80.48 | 80.24 | 75.48 | 70.71 |
| landing-038-bold-typography | A | landing | 100.00 | 100.00 | 100.00 | 85.71 |
| landing-039-blade-runner-noir | A | landing | 78.57 | 84.29 | 80.71 | 80.24 |
| landing-040-letterpress | A | landing | 89.05 | 91.43 | 89.05 | 77.38 |
| landing-041-stop-motion-craft | A | landing | 68.10 | 78.10 | 58.57 | 61.67 |
| landing-042-blueprint-paper | A | landing | 91.43 | 92.62 | 89.05 | 76.67 |
| landing-043-brutalist-graphic-design | A | landing | 79.29 | 96.19 | 91.43 | 87.86 |
| landing-045-glassmorphism | A | landing | 96.53 | 90.00 | 83.20 | 83.81 |
| landing-046-lunarpunk | A | landing | 73.57 | 87.86 | 78.57 | 86.43 |
| landing-047-chalkboard-slate | A | landing | 100.00 | 90.00 | 81.67 | 87.38 |
| landing-048-club-poster-ui | A | landing | 91.43 | 69.29 | 80.00 | 77.86 |
| landing-049-japandi | A | landing | 88.57 | 91.43 | 92.86 | 92.86 |
| landing-050-leather-bound | A | landing | 90.41 | 86.33 | 97.96 | 74.90 |
| landing-051-skate-mag | A | landing | 100.00 | 88.57 | 92.14 | 100.00 |
| landing-052-armin-hofmann-contrast-and-reduction | A | landing | 80.95 | 69.52 | 75.71 | 75.71 |
| landing-053-cyberpunk | A | landing | 80.00 | 86.43 | 72.62 | 76.19 |
| landing-054-maritime-heritage-editorial | A | landing | 93.81 | 89.78 | 100.00 | 46.91 |
| landing-055-mid-century-modern | A | landing | 100.00 | 92.86 | 90.24 | 95.71 |
| landing-056-canvas-fabric | A | landing | 95.00 | 88.41 | 93.41 | 95.00 |
| landing-057-space-documentary | A | landing | 76.19 | 91.43 | 81.90 | 90.00 |
| landing-058-streetwear-drop | A | landing | 89.05 | 87.14 | 81.43 | 82.38 |
| landing-059-art-nouveau | A | landing | 82.86 | 82.86 | 76.05 | 78.20 |
| landing-060-dieter-rams-silent-control-panel | A | landing | 83.69 | 89.05 | 72.74 | 52.98 |
| landing-061-pop-art | A | landing | 90.00 | 93.81 | 90.95 | 88.10 |
| landing-062-cottagecore | A | landing | 77.62 | 84.76 | 56.67 | 64.76 |
| landing-063-luxury-fashion-film | A | landing | 78.57 | 72.86 | 65.48 | 78.57 |
| landing-064-op-art | A | landing | 96.53 | 74.73 | 100.00 | 71.67 |
| landing-066-color-field | A | landing | 88.10 | 62.93 | 82.35 | 77.48 |
| landing-067-wabi-sabi | A | landing | 95.24 | 95.24 | 100.00 | 85.95 |
| landing-068-dreamcore | A | landing | 92.86 | 78.10 | 91.67 | 81.67 |
| landing-069-goblincore | A | landing | 75.71 | 73.57 | 87.86 | 65.71 |
| landing-070-susan-kare-pixel-icon-clarity | A | landing | 89.39 | 87.14 | 74.01 | 76.67 |
| landing-071-logistics-industrial | A | landing | 81.43 | 86.19 | 69.76 | 79.05 |
| landing-072-steampunk | A | landing | 96.43 | 80.24 | 72.38 | 95.24 |
| landing-073-luxury | A | landing | 95.00 | 91.43 | 90.00 | 90.00 |
| landing-074-solarpunk | A | landing | 81.67 | 82.86 | 68.57 | 78.10 |
| landing-076-massimo-vignelli-typographic-discipline | A | landing | 93.81 | 96.79 | 91.43 | 89.17 |
| landing-077-material-you-expressive | A | landing | 96.19 | 81.90 | 73.33 | 49.29 |
| landing-078-vaporwave | A | landing | 80.20 | 84.97 | 87.62 | 71.05 |
| landing-079-kidcore | A | landing | 96.43 | 96.43 | 95.00 | 91.67 |
| landing-081-frutiger-aero | A | landing | 83.81 | 93.81 | 100.00 | 85.24 |
| landing-082-laszlo-moholy-nagy-light-and-new-media | A | landing | 92.14 | 85.48 | 92.86 | 82.62 |
| landing-083-legal-authority | A | landing | 87.38 | 90.24 | 95.24 | 84.05 |
| landing-084-persian-islamic-geometric | A | landing | 86.31 | 70.71 | 50.83 | 61.31 |
| landing-085-quiet-luxury | A | landing | 100.00 | 95.00 | 86.43 | 95.00 |
| landing-086-skeuomorphic-premium | A | landing | 85.00 | 91.43 | 100.00 | 78.57 |
| landing-088-gothic-revival | A | landing | 86.43 | 85.71 | 90.00 | 90.00 |
| landing-089-neumorphism | A | landing | 92.38 | 93.81 | 88.20 | 81.77 |
| landing-091-watercolor-wash | A | landing | 82.86 | 80.00 | 64.29 | 67.86 |
| landing-093-grunge | A | landing | 82.86 | 92.86 | 84.29 | 67.86 |
| landing-094-josef-mueller-brockmann-swiss-grid-rhythm | A | landing | 88.57 | 90.00 | 55.44 | 90.82 |
| landing-095-velvet-luxury | A | landing | 80.20 | 87.35 | 93.06 | 87.35 |
| landing-096-industrial | A | landing | 100.00 | 80.71 | 85.00 | 100.00 |
| landing-098-impressionism | A | landing | 87.96 | 74.86 | 83.20 | 92.72 |
| landing-099-denis-villeneuve-sci-fi | A | landing | 87.86 | 91.43 | 91.43 | 86.43 |
| landing-100-dada-collage | A | landing | 77.86 | 69.29 | 59.29 | 75.71 |
| landing-101-fairycore | A | landing | 85.48 | 84.05 | 74.05 | 74.05 |
| landing-102-weirdcore | A | landing | 87.86 | 85.71 | 84.29 | 77.14 |
| landing-103-ikko-tanaka-tradition-as-geometry | A | landing | 79.05 | 78.10 | 86.67 | 75.71 |
| landing-104-gorpcore-outdoor-tech | A | landing | 83.81 | 86.67 | 88.10 | 93.81 |
| landing-105-holographic-foil | A | landing | 100.00 | 91.43 | 87.86 | 84.29 |
| landing-106-mermaidcore | A | landing | 77.38 | 91.67 | 83.57 | 85.95 |
| landing-107-neo-brutalism | A | landing | 100.00 | 83.57 | 96.43 | 90.71 |
| landing-108-cubism | A | landing | 91.77 | 95.24 | 85.92 | 67.38 |
| landing-109-manga-panel-ui | A | landing | 91.07 | 84.64 | 73.10 | 76.67 |
| landing-110-blackout-xerox-punk | A | landing | 69.76 | 69.76 | 60.24 | 70.24 |
| landing-111-cyberdelic | A | landing | 86.67 | 84.29 | 95.24 | 83.81 |
| landing-112-matte-ceramic | A | landing | 93.57 | 92.14 | 100.00 | 93.57 |
| landing-113-studio-ghibli-whimsy | A | landing | 83.81 | 83.81 | 81.67 | 83.10 |
| landing-114-futurism | A | landing | 100.00 | 96.43 | 100.00 | 90.24 |
| track-b-dashboard-001-src-368 | B | dashboard | 69.93 | 92.24 | 91.36 | 70.75 |
| track-b-dashboard-002-src-370 | B | dashboard | 86.43 | 85.36 | 89.64 | 88.21 |
| track-b-dashboard-003-src-371 | B | dashboard | 93.81 | 50.83 | 73.09 | 45.71 |
| track-b-dashboard-004-src-373 | B | dashboard | 90.00 | 81.67 | 76.02 | 68.91 |
| track-b-dashboard-005-src-375 | B | dashboard | 95.00 | 85.24 | 59.44 | 57.40 |
| track-b-dashboard-006-src-376 | B | dashboard | 100.00 | 79.76 | 89.52 | 85.00 |
| track-b-dashboard-007-src-378 | B | dashboard | 100.00 | 96.04 | 85.27 | 43.92 |
| track-b-dashboard-008-src-380 | B | dashboard | 89.76 | 95.00 | 89.76 | 73.81 |
| track-b-dashboard-009-src-382 | B | dashboard | 91.43 | 98.57 | 93.81 | 79.52 |
| track-b-dashboard-010-src-383 | B | dashboard | 73.33 | 77.74 | 56.19 | 68.09 |
| track-b-dashboard-011-src-385 | B | dashboard | 81.69 | 85.71 | 82.86 | 71.10 |
| track-b-dashboard-012-src-387 | B | dashboard | 86.70 | 74.32 | 80.33 | 70.22 |
| track-b-dashboard-013-src-388 | B | dashboard | 88.76 | 91.28 | 90.22 | 78.61 |
| track-b-dashboard-014-src-390 | B | dashboard | 100.00 | 80.20 | 85.31 | 83.67 |
| track-b-dashboard-015-src-392 | B | dashboard | 84.29 | 78.57 | 62.14 | 89.29 |
| track-b-dashboard-016-src-393 | B | dashboard | 68.88 | 40.75 | 63.88 | 49.12 |
| track-b-dashboard-017-src-395 | B | dashboard | 100.00 | 85.24 | 81.19 | 92.14 |
| track-b-dashboard-018-src-397 | B | dashboard | 95.97 | 86.49 | 93.25 | 85.06 |
| track-b-dashboard-019-src-398 | B | dashboard | 100.00 | 92.14 | 81.43 | 90.71 |
| track-b-dashboard-020-src-400 | B | dashboard | 90.68 | 94.49 | 85.78 | 83.91 |
| track-b-dashboard-021-src-402 | B | dashboard | 97.14 | 93.97 | 73.02 | 86.35 |
| track-b-dashboard-022-src-403 | B | dashboard | 86.67 | 51.75 | 80.16 | 70.32 |
| track-b-dashboard-023-src-405 | B | dashboard | 85.71 | 73.19 | 63.04 | 37.84 |
| track-b-dashboard-024-src-407 | B | dashboard | 100.00 | 98.57 | 51.51 | 71.75 |
| track-b-dashboard-025-src-409 | B | dashboard | 98.57 | 85.00 | 54.29 | 71.43 |
| track-b-dashboard-026-src-410 | B | dashboard | 75.00 | 88.57 | 75.71 | 80.71 |
| track-b-dashboard-027-src-412 | B | dashboard | 87.62 | 89.52 | 82.86 | 63.81 |
| track-b-dashboard-028-src-414 | B | dashboard | 82.14 | 85.00 | 78.57 | 81.43 |
| track-b-dashboard-029-src-415 | B | dashboard | 84.76 | 70.48 | 68.10 | 50.00 |
| track-b-dashboard-030-src-417 | B | dashboard | 100.00 | 89.29 | 63.10 | 60.71 |
| track-b-landing-001-src-268 | B | landing | 69.39 | 72.24 | 72.96 | 88.57 |
| track-b-landing-002-src-271 | B | landing | 100.00 | 92.14 | 91.43 | 87.86 |
| track-b-landing-003-src-275 | B | landing | 77.14 | 71.90 | 65.24 | 83.81 |
| track-b-landing-004-src-278 | B | landing | 100.00 | 76.50 | 66.63 | 85.34 |
| track-b-landing-005-src-282 | B | landing | 91.67 | 98.57 | 95.00 | 91.79 |
| track-b-landing-006-src-285 | B | landing | 84.29 | 77.30 | 87.62 | 81.91 |
| track-b-landing-007-src-288 | B | landing | 93.81 | 82.38 | 93.81 | 90.60 |
| track-b-landing-008-src-292 | B | landing | 93.81 | 92.86 | 79.29 | 81.07 |
| track-b-landing-009-src-295 | B | landing | 75.80 | 70.50 | 74.39 | 81.99 |
| track-b-landing-010-src-299 | B | landing | 95.40 | 88.81 | 91.98 | 98.57 |
| track-b-landing-011-src-302 | B | landing | 100.00 | 82.11 | 86.26 | 88.30 |
| track-b-landing-012-src-306 | B | landing | 84.64 | 90.00 | 87.02 | 72.50 |
| track-b-landing-013-src-309 | B | landing | 84.52 | 90.24 | 93.81 | 74.01 |
| track-b-landing-014-src-312 | B | landing | 95.56 | 95.56 | 94.13 | 92.70 |
| track-b-landing-015-src-316 | B | landing | 93.81 | 97.14 | 81.91 | 84.76 |
| track-b-landing-016-src-319 | B | landing | 95.71 | 100.00 | 95.71 | 35.08 |
| track-b-landing-017-src-323 | B | landing | 100.00 | 93.81 | 91.77 | 61.84 |
| track-b-landing-018-src-326 | B | landing | 100.00 | 96.19 | 81.27 | 74.05 |
| track-b-landing-019-src-329 | B | landing | 87.62 | 81.90 | 68.73 | 84.60 |
| track-b-landing-020-src-333 | B | landing | 78.41 | 75.79 | 100.00 | 86.03 |
| track-b-landing-021-src-336 | B | landing | 95.24 | 90.24 | 79.52 | 95.97 |
| track-b-landing-022-src-340 | B | landing | 97.14 | 100.00 | 100.00 | 92.96 |
| track-b-landing-023-src-343 | B | landing | 83.81 | 74.52 | 83.10 | 85.24 |
| track-b-landing-024-src-347 | B | landing | 91.43 | 92.86 | 88.41 | 90.40 |
| track-b-landing-025-src-350 | B | landing | 94.29 | 100.00 | 97.14 | 88.81 |
| track-b-landing-026-src-353 | B | landing | 87.38 | 84.29 | 86.67 | 93.81 |
| track-b-landing-027-src-357 | B | landing | 95.24 | 78.45 | 88.45 | 88.45 |
| track-b-landing-028-src-360 | B | landing | 92.35 | 90.31 | 71.46 | 65.99 |
| track-b-landing-029-src-364 | B | landing | 100.00 | 100.00 | 95.24 | 100.00 |
| track-b-landing-030-src-367 | B | landing | 89.05 | 91.77 | 100.00 | 78.03 |
Hover a score to read the judge summary. Highlighted cell = best model on that case. Reference column: 4B Muon step200.
+| case_id | track | surface | 27B AdamW step400 | 9B AdamW step200 | 4B AdamW step200 | 4B Muon step200 |
|---|---|---|---|---|---|---|
| dashboard-002-armin-hofmann-contrast-and-reduction | A | dashboard | 45.65 | 78.19 | 75.95 | 42.16 |
| dashboard-003-blueprint-hologram-console | A | dashboard | 67.25 | 76.99 | 88.95 | 67.90 |
| dashboard-004-dashboard-brutalism | A | dashboard | 95.59 | 94.42 | 84.95 | 75.64 |
| dashboard-005-dieter-rams-silent-control-panel | A | dashboard | 76.16 | 63.06 | 83.91 | 51.65 |
| dashboard-006-carbon-fiber-telemetry | A | dashboard | 55.79 | 73.27 | 72.36 | 66.98 |
| dashboard-007-ceramic-bento-metrics | A | dashboard | 80.91 | 51.15 | 59.78 | 73.77 |
| dashboard-008-admin-crud-panel | A | dashboard | 85.88 | 45.35 | 60.17 | 39.47 |
| dashboard-009-arcade-cabinet-ops | A | dashboard | 59.81 | 77.72 | 38.59 | 51.02 |
| dashboard-011-anime-dashboard | A | dashboard | 99.30 | 73.59 | 78.40 | 42.85 |
| dashboard-012-glass-cockpit-avionics | A | dashboard | 90.42 | 88.21 | 67.16 | 39.28 |
| dashboard-013-bauhaus | A | dashboard | 90.02 | 66.33 | 86.80 | 75.48 |
| dashboard-014-developer-first-minimal | A | dashboard | 84.86 | 90.38 | 68.38 | 61.76 |
| dashboard-015-ev-instrument-cluster | A | dashboard | 97.36 | 62.42 | 54.68 | 42.92 |
| dashboard-016-financial-broadsheet | A | dashboard | 84.58 | 69.94 | 57.29 | 56.27 |
| dashboard-018-crypto-dashboard | A | dashboard | 90.86 | 76.97 | 48.40 | 78.64 |
| dashboard-019-executive-kpi-dashboard | A | dashboard | 85.95 | 76.02 | 60.58 | 68.02 |
| dashboard-020-data-storytelling-ui | A | dashboard | 65.42 | 54.45 | 78.07 | 53.85 |
| dashboard-021-fluent-design | A | dashboard | 85.33 | 69.64 | 82.61 | 52.03 |
| dashboard-023-adaptive-ambient-ui | A | dashboard | 89.89 | 85.48 | 56.88 | 64.80 |
| dashboard-024-honeycomb-paper-ledger | A | dashboard | 80.17 | 67.95 | 69.31 | 60.99 |
| dashboard-027-kenya-hara-white-and-emptiness | A | dashboard | 83.19 | 77.73 | 72.08 | 55.17 |
| dashboard-029-lime-noir-logistics-glass | A | dashboard | 84.93 | 74.90 | 71.96 | 61.31 |
| dashboard-030-lucky-swaps-volumetric-console | A | dashboard | 89.08 | 70.27 | 76.35 | 70.99 |
| dashboard-031-mac-os-aqua-nostalgia | A | dashboard | 82.47 | 55.18 | 71.18 | 56.10 |
| dashboard-032-massimo-vignelli-typographic-discipline | A | dashboard | 83.29 | 88.00 | 85.55 | 79.27 |
| dashboard-033-motorsport-pit-wall | A | dashboard | 72.12 | 51.60 | 57.59 | 49.39 |
| dashboard-035-observability-dark | A | dashboard | 94.61 | 87.41 | 64.77 | 71.01 |
| dashboard-036-obsidian-aura-portfolio | A | dashboard | 71.05 | 61.03 | 52.98 | 50.88 |
| dashboard-037-pale-grid-node-console | A | dashboard | 78.26 | 87.89 | 61.94 | 61.33 |
| dashboard-039-retro-lcd-control-panel | A | dashboard | 75.78 | 68.29 | 72.13 | 55.70 |
| dashboard-040-rpg-guild-operations | A | dashboard | 94.96 | 74.70 | 97.57 | 70.08 |
| dashboard-041-scada-hmi-industrial | A | dashboard | 74.49 | 75.23 | 54.42 | 49.71 |
| dashboard-042-soft-rubber-control-room | A | dashboard | 94.10 | 92.71 | 80.65 | 60.49 |
| dashboard-043-split-flap-departure-board | A | dashboard | 78.91 | 48.69 | 78.54 | 29.13 |
| dashboard-044-sticker-sheet-analytics | A | dashboard | 90.69 | 83.89 | 55.00 | 65.65 |
| dashboard-045-streaming-dashboard-obs | A | dashboard | 13.09 | 74.67 | 84.84 | 33.82 |
| dashboard-046-studded-brick-ops | A | dashboard | 82.35 | 63.58 | 78.45 | 46.08 |
| dashboard-047-susan-kare-pixel-icon-clarity | A | dashboard | 73.98 | 61.71 | 55.42 | 34.69 |
| dashboard-048-teenage-engineering-industrial | A | dashboard | 83.64 | 82.30 | 63.14 | 68.35 |
| dashboard-049-topographic-terrain-console | A | dashboard | 93.23 | 63.36 | 50.67 | 44.85 |
| landing-001-1970s-documentary | A | landing | 91.83 | 85.44 | 95.56 | 85.23 |
| landing-002-afrofuturism | A | landing | 94.96 | 94.17 | 83.55 | 88.02 |
| landing-003-1980s-arcade-cinema | A | landing | 94.76 | 100.00 | 95.95 | 62.55 |
| landing-004-70s-warm-retro | A | landing | 95.60 | 78.32 | 78.39 | 56.58 |
| landing-005-april-greiman-digital-collage | A | landing | 62.65 | 84.90 | 66.53 | 97.18 |
| landing-006-acid-graphics | A | landing | 96.16 | 69.08 | 88.00 | 76.74 |
| landing-007-a24-indie-editorial | A | landing | 96.39 | 91.40 | 94.64 | 90.97 |
| landing-008-abstract-expressionism | A | landing | 87.10 | 96.35 | 76.17 | 72.23 |
| landing-009-adaptive-ambient-ui | A | landing | 99.52 | 79.05 | 86.75 | 55.49 |
| landing-011-80s-synthwave | A | landing | 84.38 | 66.82 | 82.18 | 85.89 |
| landing-012-academia | A | landing | 98.61 | 99.40 | 66.23 | 89.74 |
| landing-013-bohemian | A | landing | 89.32 | 93.93 | 88.33 | 83.80 |
| landing-015-biomorphic-design | A | landing | 73.57 | 85.51 | 81.88 | 74.48 |
| landing-016-de-stijl | A | landing | 99.40 | 77.12 | 98.53 | 86.41 |
| landing-017-anodized-metal | A | landing | 83.06 | 93.21 | 89.68 | 75.77 |
| landing-018-indie-sleaze-2005 | A | landing | 83.86 | 94.46 | 93.45 | 58.85 |
| landing-019-paul-rand-modernist-wit | A | landing | 68.08 | 95.24 | 95.21 | 80.10 |
| landing-020-arc-browser-like-playful-productivity | A | landing | 98.14 | 98.35 | 91.29 | 89.48 |
| landing-023-coastal-grandmother | A | landing | 94.08 | 96.31 | 86.28 | 93.10 |
| landing-025-bauhaus | A | landing | 81.64 | 58.22 | 83.48 | 61.30 |
| landing-026-carbon-fiber | A | landing | 90.56 | 98.81 | 79.32 | 74.67 |
| landing-027-art-deco | A | landing | 85.87 | 98.81 | 84.70 | 78.66 |
| landing-028-christopher-nolan-esque | A | landing | 91.72 | 91.55 | 66.42 | 73.87 |
| landing-029-aurora-mesh | A | landing | 93.45 | 92.30 | 82.50 | 82.02 |
| landing-031-kubrick-symmetry | A | landing | 90.99 | 99.21 | 99.21 | 94.56 |
| landing-032-scandinavian-minimal | A | landing | 99.66 | 96.68 | 93.87 | 83.59 |
| landing-033-underground-brutalism | A | landing | 89.56 | 87.09 | 89.50 | 87.37 |
| landing-034-brushed-aluminum | A | landing | 89.40 | 75.32 | 78.31 | 68.47 |
| landing-035-linen-texture | A | landing | 94.33 | 87.20 | 86.19 | 88.72 |
| landing-036-energy-utility | A | landing | 100.00 | 97.78 | 99.40 | 81.75 |
| landing-037-constructivism | A | landing | 71.97 | 91.94 | 94.72 | 86.69 |
| landing-038-bold-typography | A | landing | 80.41 | 89.32 | 89.32 | 78.54 |
| landing-039-blade-runner-noir | A | landing | 73.55 | 78.73 | 92.02 | 71.33 |
| landing-040-letterpress | A | landing | 93.41 | 72.97 | 84.23 | 63.71 |
| landing-041-stop-motion-craft | A | landing | 74.55 | 85.52 | 84.82 | 88.85 |
| landing-042-blueprint-paper | A | landing | 77.56 | 96.39 | 75.19 | 82.18 |
| landing-043-brutalist-graphic-design | A | landing | 84.05 | 87.82 | 85.71 | 95.60 |
| landing-045-glassmorphism | A | landing | 94.66 | 71.33 | 90.06 | 78.29 |
| landing-046-lunarpunk | A | landing | 93.21 | 93.21 | 69.28 | 55.26 |
| landing-047-chalkboard-slate | A | landing | 93.09 | 95.95 | 83.25 | 83.79 |
| landing-048-club-poster-ui | A | landing | 89.52 | 88.93 | 68.15 | 91.55 |
| landing-049-japandi | A | landing | 95.71 | 78.51 | 79.63 | 83.30 |
| landing-050-leather-bound | A | landing | 87.09 | 91.77 | 99.66 | 70.09 |
| landing-051-skate-mag | A | landing | 98.81 | 89.76 | 87.13 | 84.44 |
| landing-052-armin-hofmann-contrast-and-reduction | A | landing | 76.41 | 91.35 | 91.19 | 81.07 |
| landing-053-cyberpunk | A | landing | 87.02 | 91.79 | 82.82 | 70.67 |
| landing-054-maritime-heritage-editorial | A | landing | 94.21 | 83.47 | 86.79 | 62.03 |
| landing-055-mid-century-modern | A | landing | 83.90 | 72.30 | 97.18 | 86.82 |
| landing-056-canvas-fabric | A | landing | 97.98 | 81.76 | 95.93 | 76.52 |
| landing-057-space-documentary | A | landing | 89.96 | 83.99 | 95.79 | 80.65 |
| landing-058-streetwear-drop | A | landing | 87.99 | 82.14 | 77.62 | 70.39 |
| landing-059-art-nouveau | A | landing | 81.55 | 85.83 | 76.88 | 60.45 |
| landing-060-dieter-rams-silent-control-panel | A | landing | 69.81 | 85.56 | 85.22 | 60.51 |
| landing-061-pop-art | A | landing | 71.53 | 97.78 | 97.30 | 87.73 |
| landing-062-cottagecore | A | landing | 84.25 | 86.75 | 62.18 | 60.78 |
| landing-063-luxury-fashion-film | A | landing | 77.98 | 86.55 | 89.48 | 75.69 |
| landing-064-op-art | A | landing | 84.30 | 85.67 | 100.00 | 83.97 |
| landing-066-color-field | A | landing | 94.44 | 75.07 | 92.89 | 61.36 |
| landing-067-wabi-sabi | A | landing | 94.84 | 89.56 | 96.43 | 76.71 |
| landing-068-dreamcore | A | landing | 97.62 | 66.70 | 98.61 | 76.46 |
| landing-069-goblincore | A | landing | 85.41 | 94.40 | 90.00 | 53.20 |
| landing-070-susan-kare-pixel-icon-clarity | A | landing | 82.03 | 85.10 | 81.03 | 61.77 |
| landing-071-logistics-industrial | A | landing | 94.52 | 94.01 | 83.53 | 88.07 |
| landing-072-steampunk | A | landing | 99.40 | 80.99 | 65.69 | 73.77 |
| landing-073-luxury | A | landing | 97.98 | 93.81 | 92.38 | 82.30 |
| landing-074-solarpunk | A | landing | 79.14 | 80.47 | 68.30 | 76.17 |
| landing-076-massimo-vignelli-typographic-discipline | A | landing | 94.21 | 98.27 | 92.02 | 69.41 |
| landing-077-material-you-expressive | A | landing | 85.90 | 81.32 | 80.61 | 57.01 |
| landing-078-vaporwave | A | landing | 84.85 | 72.92 | 86.80 | 84.04 |
| landing-079-kidcore | A | landing | 99.40 | 99.40 | 68.97 | 86.41 |
| landing-081-frutiger-aero | A | landing | 86.94 | 79.15 | 82.50 | 77.12 |
| landing-082-laszlo-moholy-nagy-light-and-new-media | A | landing | 87.14 | 95.20 | 83.75 | 67.71 |
| landing-083-legal-authority | A | landing | 67.63 | 88.85 | 95.63 | 62.44 |
| landing-084-persian-islamic-geometric | A | landing | 96.53 | 88.45 | 55.40 | 82.00 |
| landing-085-quiet-luxury | A | landing | 100.00 | 97.98 | 91.79 | 96.19 |
| landing-086-skeuomorphic-premium | A | landing | 90.95 | 81.67 | 100.00 | 72.55 |
| landing-088-gothic-revival | A | landing | 88.69 | 95.24 | 97.14 | 94.34 |
| landing-089-neumorphism | A | landing | 91.59 | 88.31 | 87.38 | 68.80 |
| landing-091-watercolor-wash | A | landing | 94.76 | 91.90 | 76.79 | 74.95 |
| landing-093-grunge | A | landing | 88.84 | 89.46 | 96.19 | 70.04 |
| landing-094-josef-mueller-brockmann-swiss-grid-rhythm | A | landing | 91.43 | 86.73 | 47.06 | 96.09 |
| landing-095-velvet-luxury | A | landing | 91.94 | 96.70 | 92.89 | 86.38 |
| landing-096-industrial | A | landing | 91.07 | 76.60 | 87.38 | 83.10 |
| landing-098-impressionism | A | landing | 92.04 | 89.86 | 88.67 | 85.69 |
| landing-099-denis-villeneuve-sci-fi | A | landing | 96.79 | 90.58 | 92.62 | 93.57 |
| landing-100-dada-collage | A | landing | 69.30 | 79.78 | 71.28 | 76.51 |
| landing-101-fairycore | A | landing | 91.08 | 83.23 | 81.15 | 61.49 |
| landing-102-weirdcore | A | landing | 96.79 | 84.63 | 96.19 | 62.54 |
| landing-103-ikko-tanaka-tradition-as-geometry | A | landing | 74.65 | 71.63 | 62.56 | 77.98 |
| landing-104-gorpcore-outdoor-tech | A | landing | 92.54 | 88.73 | 74.90 | 94.21 |
| landing-105-holographic-foil | A | landing | 100.00 | 87.02 | 80.65 | 96.19 |
| landing-106-mermaidcore | A | landing | 90.28 | 98.61 | 96.07 | 89.92 |
| landing-107-neo-brutalism | A | landing | 100.00 | 91.31 | 84.17 | 86.31 |
| landing-108-cubism | A | landing | 97.44 | 77.94 | 91.70 | 90.99 |
| landing-109-manga-panel-ui | A | landing | 88.87 | 78.21 | 82.82 | 78.85 |
| landing-110-blackout-xerox-punk | A | landing | 82.22 | 65.13 | 80.75 | 50.68 |
| landing-111-cyberdelic | A | landing | 96.59 | 87.14 | 81.71 | 72.64 |
| landing-112-matte-ceramic | A | landing | 98.93 | 77.66 | 90.94 | 86.79 |
| landing-113-studio-ghibli-whimsy | A | landing | 94.92 | 94.92 | 76.59 | 82.05 |
| landing-114-futurism | A | landing | 100.00 | 90.95 | 100.00 | 93.61 |
| track-b-dashboard-001-src-368 | B | dashboard | 82.05 | 67.70 | 87.61 | 63.97 |
| track-b-dashboard-002-src-370 | B | dashboard | 83.58 | 65.53 | 91.79 | 78.48 |
| track-b-dashboard-003-src-371 | B | dashboard | 88.73 | 55.64 | 86.83 | 47.46 |
| track-b-dashboard-004-src-373 | B | dashboard | 72.07 | 71.20 | 60.13 | 42.49 |
| track-b-dashboard-005-src-375 | B | dashboard | 88.72 | 85.78 | 68.42 | 46.74 |
| track-b-dashboard-006-src-376 | B | dashboard | 92.76 | 65.73 | 76.19 | 51.28 |
| track-b-dashboard-007-src-378 | B | dashboard | 89.00 | 71.67 | 70.16 | 55.41 |
| track-b-dashboard-008-src-380 | B | dashboard | 79.07 | 75.98 | 79.71 | 55.30 |
| track-b-dashboard-009-src-382 | B | dashboard | 80.09 | 85.65 | 86.80 | 58.79 |
| track-b-dashboard-010-src-383 | B | dashboard | 73.79 | 84.72 | 53.98 | 64.63 |
| track-b-dashboard-011-src-385 | B | dashboard | 87.41 | 88.59 | 77.44 | 53.41 |
| track-b-dashboard-012-src-387 | B | dashboard | 87.00 | 52.81 | 66.98 | 56.74 |
| track-b-dashboard-013-src-388 | B | dashboard | 88.84 | 77.23 | 85.60 | 58.69 |
| track-b-dashboard-014-src-390 | B | dashboard | 86.91 | 68.64 | 63.03 | 58.50 |
| track-b-dashboard-015-src-392 | B | dashboard | 82.12 | 71.80 | 51.29 | 80.90 |
| track-b-dashboard-016-src-393 | B | dashboard | 79.12 | 58.62 | 87.47 | 60.97 |
| track-b-dashboard-017-src-395 | B | dashboard | 93.16 | 78.38 | 57.45 | 77.85 |
| track-b-dashboard-018-src-397 | B | dashboard | 90.19 | 62.23 | 89.66 | 60.64 |
| track-b-dashboard-019-src-398 | B | dashboard | 78.69 | 78.09 | 70.27 | 68.95 |
| track-b-dashboard-020-src-400 | B | dashboard | 90.60 | 81.73 | 77.79 | 69.55 |
| track-b-dashboard-021-src-402 | B | dashboard | 83.18 | 84.65 | 53.81 | 60.51 |
| track-b-dashboard-022-src-403 | B | dashboard | 88.14 | 62.84 | 64.20 | 67.41 |
| track-b-dashboard-023-src-405 | B | dashboard | 90.38 | 80.26 | 81.01 | 41.73 |
| track-b-dashboard-024-src-407 | B | dashboard | 93.40 | 90.69 | 57.24 | 57.91 |
| track-b-dashboard-025-src-409 | B | dashboard | 84.20 | 82.02 | 56.01 | 57.91 |
| track-b-dashboard-026-src-410 | B | dashboard | 65.78 | 69.23 | 68.11 | 69.62 |
| track-b-dashboard-027-src-412 | B | dashboard | 90.01 | 70.53 | 74.79 | 52.31 |
| track-b-dashboard-028-src-414 | B | dashboard | 79.97 | 79.30 | 57.91 | 70.69 |
| track-b-dashboard-029-src-415 | B | dashboard | 90.89 | 81.52 | 58.35 | 47.22 |
| track-b-dashboard-030-src-417 | B | dashboard | 88.30 | 90.04 | 52.81 | 48.96 |
| track-b-landing-001-src-268 | B | landing | 75.26 | 82.87 | 80.41 | 90.95 |
| track-b-landing-002-src-271 | B | landing | 100.00 | 70.53 | 92.62 | 88.06 |
| track-b-landing-003-src-275 | B | landing | 92.62 | 92.94 | 78.73 | 90.16 |
| track-b-landing-004-src-278 | B | landing | 100.00 | 75.05 | 79.13 | 73.62 |
| track-b-landing-005-src-282 | B | landing | 98.61 | 80.80 | 76.27 | 77.54 |
| track-b-landing-006-src-285 | B | landing | 85.83 | 80.67 | 82.63 | 93.41 |
| track-b-landing-007-src-288 | B | landing | 94.21 | 59.78 | 87.66 | 86.10 |
| track-b-landing-008-src-292 | B | landing | 97.78 | 91.67 | 83.20 | 80.94 |
| track-b-landing-009-src-295 | B | landing | 91.21 | 91.51 | 83.11 | 76.72 |
| track-b-landing-010-src-299 | B | landing | 94.47 | 95.75 | 92.71 | 88.68 |
| track-b-landing-011-src-302 | B | landing | 100.00 | 84.26 | 88.58 | 87.24 |
| track-b-landing-012-src-306 | B | landing | 82.92 | 71.55 | 90.10 | 91.85 |
| track-b-landing-013-src-309 | B | landing | 97.42 | 97.18 | 83.24 | 78.00 |
| track-b-landing-014-src-312 | B | landing | 95.69 | 88.12 | 80.78 | 68.09 |
| track-b-landing-015-src-316 | B | landing | 85.34 | 79.52 | 93.41 | 86.03 |
| track-b-landing-016-src-319 | B | landing | 86.19 | 91.07 | 98.10 | 41.18 |
| track-b-landing-017-src-323 | B | landing | 100.00 | 92.82 | 75.05 | 51.85 |
| track-b-landing-018-src-326 | B | landing | 100.00 | 81.26 | 90.93 | 84.96 |
| track-b-landing-019-src-329 | B | landing | 95.56 | 88.65 | 77.82 | 82.72 |
| track-b-landing-020-src-333 | B | landing | 80.63 | 92.39 | 94.05 | 93.51 |
| track-b-landing-021-src-336 | B | landing | 99.21 | 90.38 | 76.40 | 75.19 |
| track-b-landing-022-src-340 | B | landing | 75.49 | 96.43 | 100.00 | 85.07 |
| track-b-landing-023-src-343 | B | landing | 79.15 | 93.37 | 85.63 | 88.78 |
| track-b-landing-024-src-347 | B | landing | 97.38 | 96.00 | 95.69 | 75.65 |
| track-b-landing-025-src-350 | B | landing | 91.31 | 100.00 | 93.57 | 55.95 |
| track-b-landing-026-src-353 | B | landing | 73.66 | 93.81 | 90.81 | 81.91 |
| track-b-landing-027-src-357 | B | landing | 83.01 | 74.36 | 93.31 | 87.70 |
| track-b-landing-028-src-360 | B | landing | 97.53 | 98.38 | 83.68 | 64.52 |
| track-b-landing-029-src-364 | B | landing | 94.08 | 92.66 | 90.02 | 81.42 |
| track-b-landing-030-src-367 | B | landing | 96.98 | 86.78 | 96.43 | 88.01 |
Hover a score to read the judge summary. Highlighted cell = best model on that case. Reference column: 4B Muon step200.