{
  "date": "2026-10-03",
  "mcp_version": "0.9.96",
  "floor_trials": [
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "sheet": "F01",
      "iou": 0.4441107687000775,
      "boundary_f1_1in": 0,
      "area_error_pct": 125.16905026352394,
      "seconds": 239.39760850000312,
      "cost_usd": 0.11775069504,
      "floor_shapes": 21,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "sheet": "F02",
      "iou": 0.9778369716012822,
      "boundary_f1_1in": 0.004341423746378519,
      "area_error_pct": 0.7488471922992703,
      "seconds": 391.5447200410126,
      "cost_usd": 0.20819949216,
      "floor_shapes": 13,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "sheet": "F03",
      "iou": 0.614028603104879,
      "boundary_f1_1in": 0,
      "area_error_pct": 62.85886275385697,
      "seconds": 467.0306451659999,
      "cost_usd": 0.21275726208,
      "floor_shapes": 1,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "sheet": "F04",
      "iou": 0.4978115956366477,
      "boundary_f1_1in": 0.0008183780034435324,
      "area_error_pct": 67.82610624427123,
      "seconds": 416.2228799170116,
      "cost_usd": 0.14961733248,
      "floor_shapes": 14,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "sheet": "F05",
      "iou": 0.6019950031159133,
      "boundary_f1_1in": 0.33211489689887697,
      "area_error_pct": 34.703741773773686,
      "seconds": 262.41360912501113,
      "cost_usd": 0.19283198880000002,
      "floor_shapes": 29,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "sheet": "F01",
      "iou": 0.9543319997771165,
      "boundary_f1_1in": 0.004561732219209453,
      "area_error_pct": 3.6729199542940334,
      "seconds": 503.9789294580114,
      "cost_usd": 0.1628152944,
      "floor_shapes": 15,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "sheet": "F02",
      "iou": 0.9436377671712237,
      "boundary_f1_1in": 0.006636149831464228,
      "area_error_pct": 2.888904758896947,
      "seconds": 326.6217637080117,
      "cost_usd": 0.27203014799999997,
      "floor_shapes": 8,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "sheet": "F03",
      "iou": 0.8771534140961924,
      "boundary_f1_1in": 0.017465251414317835,
      "area_error_pct": 5.15492542134953,
      "seconds": 335.6815867080004,
      "cost_usd": 0.22172043600000002,
      "floor_shapes": 12,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "sheet": "F04",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 738.513347250002,
      "cost_usd": 0.023636496,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "sheet": "F05",
      "iou": 0.8933288688497737,
      "boundary_f1_1in": 0.4597955818580338,
      "area_error_pct": 2.7174052917309326,
      "seconds": 407.22824154098635,
      "cost_usd": 0.0765157368,
      "floor_shapes": 26,
      "status": "completed"
    },
    {
      "model": "minimax/minimax-m3",
      "sheet": "F01",
      "iou": 0.14901875808510015,
      "boundary_f1_1in": 0.004374528216539147,
      "area_error_pct": 84.61944308188212,
      "seconds": 261.39004645799287,
      "cost_usd": 0.22972781999999997,
      "floor_shapes": 1,
      "status": "turn_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "sheet": "F02",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 857.8875772499887,
      "cost_usd": 0.32201561,
      "floor_shapes": 0,
      "status": "turn_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "sheet": "F03",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 498.624578500021,
      "cost_usd": 0.23880474000000002,
      "floor_shapes": 0,
      "status": "turn_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "sheet": "F04",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 1077.6867192080244,
      "cost_usd": 0.16284481,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "sheet": "F05",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 612.8149634579895,
      "cost_usd": 0.22017076,
      "floor_shapes": 0,
      "status": "turn_limit"
    },
    {
      "model": "moonshotai/kimi-k3",
      "sheet": "F01",
      "iou": 0.9343332014069585,
      "boundary_f1_1in": 0.007593544440362428,
      "area_error_pct": 4.780794869948527,
      "seconds": 270.1091958330071,
      "cost_usd": 0.8364228,
      "floor_shapes": 7,
      "status": "completed"
    },
    {
      "model": "moonshotai/kimi-k3",
      "sheet": "F02",
      "iou": 0.948668580510107,
      "boundary_f1_1in": 0.007706646807812959,
      "area_error_pct": 4.017922133257721,
      "seconds": 329.35069229101646,
      "cost_usd": 1.163175,
      "floor_shapes": 7,
      "status": "completed"
    },
    {
      "model": "moonshotai/kimi-k3",
      "sheet": "F03",
      "iou": 0.8707769733081789,
      "boundary_f1_1in": 0.15878544847094617,
      "area_error_pct": 10.799230526164463,
      "seconds": 529.9409723750141,
      "cost_usd": 1.1111536800000001,
      "floor_shapes": 8,
      "status": "turn_limit"
    },
    {
      "model": "moonshotai/kimi-k3",
      "sheet": "F04",
      "iou": 0.8980133398294864,
      "boundary_f1_1in": 0.40075703560531717,
      "area_error_pct": 0.7636543716801504,
      "seconds": 233.26239891699515,
      "cost_usd": 1.5182721000000001,
      "floor_shapes": 10,
      "status": "sheet_cost_limit"
    },
    {
      "model": "moonshotai/kimi-k3",
      "sheet": "F05",
      "iou": 0.8993407792562986,
      "boundary_f1_1in": 0.16908233726111566,
      "area_error_pct": 2.7090074788416016,
      "seconds": 727.0297916249838,
      "cost_usd": 1.3007583600000001,
      "floor_shapes": 25,
      "status": "completed"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "sheet": "F01",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 837.1146793329972,
      "cost_usd": 0.594436,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "sheet": "F02",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 966.7624881250085,
      "cost_usd": 0.5871040000000001,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "sheet": "F03",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 1399.7952198330022,
      "cost_usd": 0.687936,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "sheet": "F04",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 990.2368782919948,
      "cost_usd": 0.786588,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "sheet": "F05",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 864.8237349159899,
      "cost_usd": 0.38627799999999995,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "sheet": "F01",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 860.173312540981,
      "cost_usd": 0.084053028,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "sheet": "F02",
      "iou": 0.8799927800580001,
      "boundary_f1_1in": 0.02412268858448681,
      "area_error_pct": 10.878468289064013,
      "seconds": 766.2640332090086,
      "cost_usd": 0.08883659,
      "floor_shapes": 5,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "sheet": "F03",
      "iou": 0.8545403073031758,
      "boundary_f1_1in": 0.09221846121904773,
      "area_error_pct": 11.370017001044447,
      "seconds": 673.2481209999823,
      "cost_usd": 0.083402666,
      "floor_shapes": 9,
      "status": "turn_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "sheet": "F04",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 776.3663354169985,
      "cost_usd": 0.061969746,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "sheet": "F05",
      "iou": 0.2810369335263254,
      "boundary_f1_1in": 0.20017602724611594,
      "area_error_pct": 69.50753127705345,
      "seconds": 745.7944382500136,
      "cost_usd": 0.07758628,
      "floor_shapes": 11,
      "status": "time_limit"
    },
    {
      "model": "z-ai/glm-5.3",
      "sheet": "F01",
      "iou": 0.6006969288264488,
      "boundary_f1_1in": 0.012452196572932131,
      "area_error_pct": 41.13012501942016,
      "seconds": 161.11519575002603,
      "cost_usd": 0.6310118,
      "floor_shapes": 27,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3",
      "sheet": "F02",
      "iou": 0.8912970127068952,
      "boundary_f1_1in": 0.004655811338171526,
      "area_error_pct": 6.3005005956847615,
      "seconds": 217.51601895899512,
      "cost_usd": 0.6103746400000001,
      "floor_shapes": 14,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3",
      "sheet": "F03",
      "iou": 0.9333620293155774,
      "boundary_f1_1in": 0.09570720708752986,
      "area_error_pct": 1.4054283149223479,
      "seconds": 131.33003916702,
      "cost_usd": 0.46123744,
      "floor_shapes": 1,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3",
      "sheet": "F04",
      "iou": 0.480617755060339,
      "boundary_f1_1in": 0.2141355217068607,
      "area_error_pct": 100.7419084567879,
      "seconds": 200.8765668749984,
      "cost_usd": 0.44990051999999997,
      "floor_shapes": 21,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3",
      "sheet": "F05",
      "iou": 0.7664360979220572,
      "boundary_f1_1in": 0.4445616432033014,
      "area_error_pct": 18.655084923338418,
      "seconds": 221.2007902500045,
      "cost_usd": 0.6410550800000001,
      "floor_shapes": 35,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "sheet": "F01",
      "iou": 0.9151189149239038,
      "boundary_f1_1in": 0.0028788124548035513,
      "area_error_pct": 5.419832146286741,
      "seconds": 448.4796685829933,
      "cost_usd": 0.09069321817,
      "floor_shapes": 15,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "sheet": "F02",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 160.45991441601655,
      "cost_usd": 0.12632749000000001,
      "floor_shapes": 0,
      "status": "turn_limit"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "sheet": "F03",
      "iou": 0.0,
      "boundary_f1_1in": 0,
      "area_error_pct": 100.0,
      "seconds": 769.4688550419814,
      "cost_usd": 0.09667637235,
      "floor_shapes": 0,
      "status": "time_limit"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "sheet": "F04",
      "iou": 0.860630372424114,
      "boundary_f1_1in": 0.18564868703646498,
      "area_error_pct": 5.81253169097887,
      "seconds": 389.60746862500673,
      "cost_usd": 0.04945371,
      "floor_shapes": 11,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "sheet": "F05",
      "iou": 0.8121753960143276,
      "boundary_f1_1in": 0.22677420939263424,
      "area_error_pct": 10.835691613832596,
      "seconds": 346.112674709002,
      "cost_usd": 0.11454477,
      "floor_shapes": 27,
      "status": "turn_limit"
    }
  ],
  "base_wall_scope_scores": [
    {
      "model": "z-ai/glm-5.3",
      "scope": "base",
      "run_f1_1in": 0.6493476266745348,
      "quantity_error_pct": 24.05074600196548,
      "seconds": 407.0272966659977,
      "cost_usd": 1.1654498800000002,
      "status": "completed"
    },
    {
      "model": "z-ai/glm-5.3",
      "scope": "wall_tile",
      "run_f1_1in": 0.7963470929414697,
      "quantity_error_pct": 1.5164467951383127,
      "height_correct_predicted_area_fraction": 0.18493224240922204,
      "seconds": 407.0272966659977,
      "cost_usd": 1.1654498800000002,
      "status": "completed"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "scope": "base",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "seconds": 787.0259336669988,
      "cost_usd": 0.09167715600000001,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-flash",
      "scope": "wall_tile",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "height_correct_predicted_area_fraction": 0,
      "seconds": 787.0259336669988,
      "cost_usd": 0.09167715600000001,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "scope": "base",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "seconds": 771.8264243340236,
      "cost_usd": 0.757906,
      "status": "time_limit"
    },
    {
      "model": "qwen/qwen3.8-2.4t-a95b",
      "scope": "wall_tile",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "height_correct_predicted_area_fraction": 0,
      "seconds": 771.8264243340236,
      "cost_usd": 0.757906,
      "status": "time_limit"
    },
    {
      "model": "moonshotai/kimi-k3",
      "scope": "base",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "seconds": 610.2490477079991,
      "cost_usd": 1.586843322,
      "status": "sheet_cost_limit"
    },
    {
      "model": "moonshotai/kimi-k3",
      "scope": "wall_tile",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "height_correct_predicted_area_fraction": 0,
      "seconds": 610.2490477079991,
      "cost_usd": 1.586843322,
      "status": "sheet_cost_limit"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "scope": "base",
      "run_f1_1in": 0.4516749181055883,
      "quantity_error_pct": 45.028887102057844,
      "seconds": 540.1213092080143,
      "cost_usd": 0.14368460000000002,
      "status": "turn_limit"
    },
    {
      "model": "z-ai/glm-5.3-flash",
      "scope": "wall_tile",
      "run_f1_1in": 0.8157821200192182,
      "quantity_error_pct": 6.754202980375484,
      "height_correct_predicted_area_fraction": 0.6702205643939494,
      "seconds": 540.1213092080143,
      "cost_usd": 0.14368460000000002,
      "status": "turn_limit"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "scope": "base",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "seconds": 243.48362320798333,
      "cost_usd": 0.21320703600000002,
      "status": "turn_limit"
    },
    {
      "model": "deepseek/deepseek-v4.1-flash",
      "scope": "wall_tile",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "height_correct_predicted_area_fraction": 0,
      "seconds": 243.48362320798333,
      "cost_usd": 0.21320703600000002,
      "status": "turn_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "scope": "base",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "seconds": 330.8593024580041,
      "cost_usd": 0.11055231999999998,
      "status": "turn_limit"
    },
    {
      "model": "minimax/minimax-m3",
      "scope": "wall_tile",
      "run_f1_1in": 0,
      "quantity_error_pct": 100.0,
      "height_correct_predicted_area_fraction": 0,
      "seconds": 330.8593024580041,
      "cost_usd": 0.11055231999999998,
      "status": "turn_limit"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "scope": "base",
      "run_f1_1in": 0.5323785968716975,
      "quantity_error_pct": 18.889037791476703,
      "seconds": 720.61874854099,
      "cost_usd": 0.27270035232,
      "status": "completed"
    },
    {
      "model": "deepseek/deepseek-v4-pro-0813",
      "scope": "wall_tile",
      "run_f1_1in": 0.5040756236107724,
      "quantity_error_pct": 5.350082686174713,
      "height_correct_predicted_area_fraction": 0.30039598028937103,
      "seconds": 720.61874854099,
      "cost_usd": 0.27270035232,
      "status": "completed"
    }
  ],
  "base_wall_cost_note": "Two scope rows describe one trial; do not double-count runtime/cost.",
  "scope": "five anonymous private floor sheets; one separate six-sheet base/wall source packet",
  "inputs": "Private; source plans and reference geometry are not included."
}