{
  "models": {
    "GPT-5.6-Sol": {
      "continuity_2d_maze": {
        "correct": 754,
        "total": 850,
        "original_correct": 844,
        "original_total": 1000,
        "removed_overlap_correct": 90,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 600,
        "total": 846,
        "original_correct": 628,
        "original_total": 996,
        "removed_overlap_correct": 28,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 270,
        "total": 450,
        "original_correct": 303,
        "original_total": 600,
        "removed_overlap_correct": 33,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 540,
        "total": 890,
        "original_correct": 592,
        "original_total": 1040,
        "removed_overlap_correct": 52,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 185,
        "total": 450,
        "original_correct": 213,
        "original_total": 600,
        "removed_overlap_correct": 28,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 550,
        "total": 850,
        "original_correct": 562,
        "original_total": 1000,
        "removed_overlap_correct": 12,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 770,
        "total": 1000,
        "original_correct": 770,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 386,
        "total": 445,
        "original_correct": 511,
        "original_total": 600,
        "removed_overlap_correct": 121,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 4,
        "swap_log_sha256": "3da7eee97ae8d3f971c7432cb5c2722d2fd1244484b652dea861d378503bd1d4"
      },
      "enclosure_sheep": {
        "correct": 548,
        "total": 700,
        "original_correct": 642,
        "original_total": 1000,
        "removed_overlap_correct": 94,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 560,
        "total": 699,
        "original_correct": 639,
        "original_total": 999,
        "removed_overlap_correct": 79,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 318,
        "total": 450,
        "original_correct": 424,
        "original_total": 600,
        "removed_overlap_correct": 106,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 567,
        "total": 850,
        "original_correct": 612,
        "original_total": 1000,
        "removed_overlap_correct": 45,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 121,
        "total": 300,
        "original_correct": 130,
        "original_total": 600,
        "removed_overlap_correct": 9,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "GPT-5.5": {
      "continuity_2d_maze": {
        "correct": 572,
        "total": 850,
        "original_correct": 580,
        "original_total": 1000,
        "removed_overlap_correct": 8,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 433,
        "total": 846,
        "original_correct": 453,
        "original_total": 996,
        "removed_overlap_correct": 20,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 13,
        "total": 450,
        "original_correct": 13,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 511,
        "total": 890,
        "original_correct": 563,
        "original_total": 1040,
        "removed_overlap_correct": 52,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 59,
        "total": 450,
        "original_correct": 59,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 339,
        "total": 850,
        "original_correct": 339,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 600,
        "total": 1000,
        "original_correct": 600,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 223,
        "total": 445,
        "original_correct": 286,
        "original_total": 600,
        "removed_overlap_correct": 59,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 4,
        "swap_log_sha256": "94cb618a9382759c034f4880c2c94f8bb49eddb24215fc5e25bd92ecf0a83290"
      },
      "enclosure_sheep": {
        "correct": 471,
        "total": 700,
        "original_correct": 542,
        "original_total": 1000,
        "removed_overlap_correct": 71,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 556,
        "total": 699,
        "original_correct": 638,
        "original_total": 999,
        "removed_overlap_correct": 82,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 178,
        "total": 450,
        "original_correct": 216,
        "original_total": 600,
        "removed_overlap_correct": 38,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 551,
        "total": 850,
        "original_correct": 606,
        "original_total": 1000,
        "removed_overlap_correct": 55,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 133,
        "total": 300,
        "original_correct": 156,
        "original_total": 600,
        "removed_overlap_correct": 23,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "GPT-5.4-mini": {
      "continuity_2d_maze": {
        "correct": 149,
        "total": 850,
        "original_correct": 152,
        "original_total": 1000,
        "removed_overlap_correct": 3,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 189,
        "total": 846,
        "original_correct": 195,
        "original_total": 996,
        "removed_overlap_correct": 6,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 1,
        "total": 450,
        "original_correct": 1,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 322,
        "total": 890,
        "original_correct": 353,
        "original_total": 1040,
        "removed_overlap_correct": 31,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 276,
        "total": 850,
        "original_correct": 276,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 272,
        "total": 1000,
        "original_correct": 272,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 61,
        "total": 445,
        "original_correct": 63,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 2,
        "swap_log_sha256": "21a5f9cde91fab407191208a0899ff52801e38e758f0af58d83ff3680a509cc5"
      },
      "enclosure_sheep": {
        "correct": 180,
        "total": 700,
        "original_correct": 195,
        "original_total": 1000,
        "removed_overlap_correct": 15,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 166,
        "total": 699,
        "original_correct": 167,
        "original_total": 999,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 38,
        "total": 450,
        "original_correct": 38,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 243,
        "total": 850,
        "original_correct": 254,
        "original_total": 1000,
        "removed_overlap_correct": 11,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 133,
        "total": 300,
        "original_correct": 143,
        "original_total": 600,
        "removed_overlap_correct": 10,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Gemini-3.1-Flash-Lite": {
      "continuity_2d_maze": {
        "correct": 287,
        "total": 850,
        "original_correct": 288,
        "original_total": 1000,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 305,
        "total": 846,
        "original_correct": 309,
        "original_total": 996,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 407,
        "total": 890,
        "original_correct": 445,
        "original_total": 1040,
        "removed_overlap_correct": 38,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 338,
        "total": 850,
        "original_correct": 338,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 422,
        "total": 1000,
        "original_correct": 422,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 52,
        "total": 445,
        "original_correct": 56,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 4,
        "swap_log_sha256": "161407546619e8ad1b71115dc947ed2b353c843ec420878339e93c5d61d5ca3d"
      },
      "enclosure_sheep": {
        "correct": 442,
        "total": 700,
        "original_correct": 485,
        "original_total": 1000,
        "removed_overlap_correct": 43,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 221,
        "total": 699,
        "original_correct": 226,
        "original_total": 999,
        "removed_overlap_correct": 5,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 38,
        "total": 450,
        "original_correct": 39,
        "original_total": 600,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 608,
        "total": 850,
        "original_correct": 635,
        "original_total": 1000,
        "removed_overlap_correct": 27,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 110,
        "total": 300,
        "original_correct": 119,
        "original_total": 600,
        "removed_overlap_correct": 9,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Gemini-3.1-Pro": {
      "continuity_2d_maze": {
        "correct": 307,
        "total": 850,
        "original_correct": 317,
        "original_total": 1000,
        "removed_overlap_correct": 10,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 493,
        "total": 846,
        "original_correct": 534,
        "original_total": 996,
        "removed_overlap_correct": 41,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 33,
        "total": 450,
        "original_correct": 33,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 479,
        "total": 890,
        "original_correct": 524,
        "original_total": 1040,
        "removed_overlap_correct": 45,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 20,
        "total": 450,
        "original_correct": 20,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 441,
        "total": 850,
        "original_correct": 441,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 411,
        "total": 1000,
        "original_correct": 411,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 100,
        "total": 445,
        "original_correct": 105,
        "original_total": 600,
        "removed_overlap_correct": 3,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 2,
        "swap_log_sha256": "587de54610d6c331f0bf892049c1db2bae497361a2f31358f66275de501a692d"
      },
      "enclosure_sheep": {
        "correct": 549,
        "total": 700,
        "original_correct": 640,
        "original_total": 1000,
        "removed_overlap_correct": 91,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 532,
        "total": 699,
        "original_correct": 594,
        "original_total": 999,
        "removed_overlap_correct": 62,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 203,
        "total": 450,
        "original_correct": 244,
        "original_total": 600,
        "removed_overlap_correct": 41,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 640,
        "total": 850,
        "original_correct": 736,
        "original_total": 1000,
        "removed_overlap_correct": 96,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 156,
        "total": 300,
        "original_correct": 175,
        "original_total": 600,
        "removed_overlap_correct": 19,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Nemotron-Nano-12B-VL-v2": {
      "continuity_2d_maze": {
        "correct": 120,
        "total": 850,
        "original_correct": 126,
        "original_total": 1000,
        "removed_overlap_correct": 6,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 100,
        "total": 846,
        "original_correct": 104,
        "original_total": 996,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 257,
        "total": 890,
        "original_correct": 296,
        "original_total": 1040,
        "removed_overlap_correct": 39,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 174,
        "total": 850,
        "original_correct": 174,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 267,
        "total": 1000,
        "original_correct": 267,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 7,
        "total": 445,
        "original_correct": 8,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 1,
        "swap_log_sha256": "d6c45bede0f9c616578ad8a58168b7a854d31bddef66deba14a42aa68421fd27"
      },
      "enclosure_sheep": {
        "correct": 143,
        "total": 700,
        "original_correct": 153,
        "original_total": 1000,
        "removed_overlap_correct": 10,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 69,
        "total": 699,
        "original_correct": 70,
        "original_total": 999,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 1,
        "total": 450,
        "original_correct": 1,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 241,
        "total": 850,
        "original_correct": 246,
        "original_total": 1000,
        "removed_overlap_correct": 5,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 18,
        "total": 300,
        "original_correct": 20,
        "original_total": 600,
        "removed_overlap_correct": 2,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Qwen3.5-397B-A17B": {
      "continuity_2d_maze": {
        "correct": 119,
        "total": 850,
        "original_correct": 122,
        "original_total": 1000,
        "removed_overlap_correct": 3,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 327,
        "total": 846,
        "original_correct": 339,
        "original_total": 996,
        "removed_overlap_correct": 12,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 399,
        "total": 890,
        "original_correct": 430,
        "original_total": 1040,
        "removed_overlap_correct": 31,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 186,
        "total": 850,
        "original_correct": 186,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 426,
        "total": 1000,
        "original_correct": 426,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 55,
        "total": 445,
        "original_correct": 57,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 2,
        "swap_log_sha256": "a1b181cbf8872067bf43a2a8735eb6e529d448f09eb404b122688fa2ef3416e2"
      },
      "enclosure_sheep": {
        "correct": 66,
        "total": 700,
        "original_correct": 67,
        "original_total": 1000,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 244,
        "total": 699,
        "original_correct": 249,
        "original_total": 999,
        "removed_overlap_correct": 5,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 53,
        "total": 450,
        "original_correct": 55,
        "original_total": 600,
        "removed_overlap_correct": 2,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 311,
        "total": 850,
        "original_correct": 319,
        "original_total": 1000,
        "removed_overlap_correct": 8,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 45,
        "total": 300,
        "original_correct": 46,
        "original_total": 600,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Llama-4-Maverick-17B-128E": {
      "continuity_2d_maze": {
        "correct": 218,
        "total": 850,
        "original_correct": 225,
        "original_total": 1000,
        "removed_overlap_correct": 7,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 152,
        "total": 846,
        "original_correct": 156,
        "original_total": 996,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 318,
        "total": 890,
        "original_correct": 356,
        "original_total": 1040,
        "removed_overlap_correct": 38,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 263,
        "total": 850,
        "original_correct": 263,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 171,
        "total": 1000,
        "original_correct": 171,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 33,
        "total": 445,
        "original_correct": 38,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 5,
        "swap_log_sha256": "96bdc78a2b1b5641e2bb68ab7d1e7f8edcddfff08c39f5df5f85ed5015309380"
      },
      "enclosure_sheep": {
        "correct": 109,
        "total": 700,
        "original_correct": 115,
        "original_total": 1000,
        "removed_overlap_correct": 6,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 26,
        "total": 699,
        "original_correct": 26,
        "original_total": 999,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 11,
        "total": 450,
        "original_correct": 11,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 305,
        "total": 850,
        "original_correct": 307,
        "original_total": 1000,
        "removed_overlap_correct": 2,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 38,
        "total": 300,
        "original_correct": 46,
        "original_total": 600,
        "removed_overlap_correct": 8,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Ministral-3-14B-Instruct-2512": {
      "continuity_2d_maze": {
        "correct": 173,
        "total": 850,
        "original_correct": 181,
        "original_total": 1000,
        "removed_overlap_correct": 8,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 105,
        "total": 846,
        "original_correct": 111,
        "original_total": 996,
        "removed_overlap_correct": 6,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 256,
        "total": 890,
        "original_correct": 291,
        "original_total": 1040,
        "removed_overlap_correct": 35,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 140,
        "total": 850,
        "original_correct": 140,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 184,
        "total": 1000,
        "original_correct": 184,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 23,
        "total": 445,
        "original_correct": 25,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 2,
        "swap_log_sha256": "aba7ade2bbaa429af459e99bec626aa27e8bbfbdf7534e12bcd4d1202b7ac2b5"
      },
      "enclosure_sheep": {
        "correct": 114,
        "total": 700,
        "original_correct": 118,
        "original_total": 1000,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 51,
        "total": 699,
        "original_correct": 51,
        "original_total": 999,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 24,
        "total": 450,
        "original_correct": 24,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 407,
        "total": 850,
        "original_correct": 412,
        "original_total": 1000,
        "removed_overlap_correct": 5,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 62,
        "total": 300,
        "original_correct": 71,
        "original_total": 600,
        "removed_overlap_correct": 9,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "InternVL3.5-241B": {
      "continuity_2d_maze": {
        "correct": 146,
        "total": 850,
        "original_correct": 150,
        "original_total": 1000,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 100,
        "total": 846,
        "original_correct": 110,
        "original_total": 996,
        "removed_overlap_correct": 10,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 113,
        "total": 890,
        "original_correct": 139,
        "original_total": 1040,
        "removed_overlap_correct": 26,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 232,
        "total": 850,
        "original_correct": 232,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 195,
        "total": 1000,
        "original_correct": 195,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 25,
        "total": 445,
        "original_correct": 25,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": "68614a04969fcc7072d2a7a760f3ead6a632b793457aae88b331d77060b21cd9"
      },
      "enclosure_sheep": {
        "correct": 160,
        "total": 700,
        "original_correct": 173,
        "original_total": 1000,
        "removed_overlap_correct": 13,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 154,
        "total": 699,
        "original_correct": 155,
        "original_total": 999,
        "removed_overlap_correct": 1,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 6,
        "total": 450,
        "original_correct": 6,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 424,
        "total": 850,
        "original_correct": 435,
        "original_total": 1000,
        "removed_overlap_correct": 11,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 22,
        "total": 300,
        "original_correct": 22,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    },
    "Gemma-4-31B-IT": {
      "continuity_2d_maze": {
        "correct": 258,
        "total": 850,
        "original_correct": 264,
        "original_total": 1000,
        "removed_overlap_correct": 6,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_3d_maze": {
        "correct": 158,
        "total": 846,
        "original_correct": 167,
        "original_total": 996,
        "removed_overlap_correct": 9,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "continuity_pipe": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_objects": {
        "correct": 170,
        "total": 890,
        "original_correct": 196,
        "original_total": 1040,
        "removed_overlap_correct": 26,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "separation_one_stroke": {
        "correct": 0,
        "total": 450,
        "original_correct": 0,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_bead_string": {
        "correct": 80,
        "total": 850,
        "original_correct": 80,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_origami": {
        "correct": 16,
        "total": 1000,
        "original_correct": 16,
        "original_total": 1000,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 0,
        "overlap_source": "no overlap",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "order_swap_2d_puzzle": {
        "correct": 6,
        "total": 445,
        "original_correct": 6,
        "original_total": 600,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": "cffb0f3b3db72865a20bec86c2ac3c5dd903e9cf2edc18fa8281d8ccc62a299a"
      },
      "enclosure_sheep": {
        "correct": 65,
        "total": 700,
        "original_correct": 86,
        "original_total": 1000,
        "removed_overlap_correct": 21,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_hole_detection": {
        "correct": 0,
        "total": 699,
        "original_correct": 0,
        "original_total": 999,
        "removed_overlap_correct": 0,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "enclosure_chat_noir": {
        "correct": 78,
        "total": 450,
        "original_correct": 82,
        "original_total": 600,
        "removed_overlap_correct": 4,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_static": {
        "correct": 53,
        "total": 850,
        "original_correct": 56,
        "original_total": 1000,
        "removed_overlap_correct": 3,
        "removed_overlap_total": 150,
        "overlap_source": "Core Easy table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      },
      "knots_untangle": {
        "correct": 59,
        "total": 300,
        "original_correct": 61,
        "original_total": 600,
        "removed_overlap_correct": 2,
        "removed_overlap_total": 300,
        "overlap_source": "Core full table",
        "removed_duplicate_correct": 0,
        "swap_log_sha256": null
      }
    }
  },
  "inputs": {
    "original_full_results": "305f290f429ba42c6836519179b99b9055fdcda8e4261cff487b152948b6bcfc",
    "release_counts": "68d19c2eff14042b06c78daf434bd213372f50d9262f167b766d5e77d5239ad4",
    "deduplication_removals": "c6c99933d7d9e8619c60447c47e2331bf7f6c43fbba12069e0d4a0a87f290a79",
    "core_table": "73e1f9e3051729f60bee34a7899c917a872fedd6b01f00b426998e0e34fa527d",
    "easy_table": "61dda3fba190ea72729e2020de064c1c0155814aa8a7d0bca1dd2a474a58966a"
  },
  "display_rates": {
    "GPT-5.6-Sol": {
      "continuity_2d_maze": 88.71,
      "continuity_3d_maze": 70.92,
      "continuity_pipe": 60.0,
      "separation_objects": 60.67,
      "separation_one_stroke": 41.11,
      "order_bead_string": 64.71,
      "order_origami": 77.0,
      "order_swap_2d_puzzle": 86.74,
      "enclosure_sheep": 78.29,
      "enclosure_hole_detection": 80.11,
      "enclosure_chat_noir": 70.67,
      "knots_static": 66.71,
      "knots_untangle": 40.33,
      "Reason": 73.39,
      "Plan": 59.77
    },
    "GPT-5.5": {
      "continuity_2d_maze": 67.29,
      "continuity_3d_maze": 51.18,
      "continuity_pipe": 2.89,
      "separation_objects": 57.42,
      "separation_one_stroke": 13.11,
      "order_bead_string": 39.88,
      "order_origami": 60.0,
      "order_swap_2d_puzzle": 50.11,
      "enclosure_sheep": 67.29,
      "enclosure_hole_detection": 79.54,
      "enclosure_chat_noir": 39.56,
      "knots_static": 64.82,
      "knots_untangle": 44.33,
      "Reason": 60.93,
      "Plan": 30.0
    },
    "GPT-5.4-mini": {
      "continuity_2d_maze": 17.53,
      "continuity_3d_maze": 22.34,
      "continuity_pipe": 0.22,
      "separation_objects": 36.18,
      "separation_one_stroke": 0.0,
      "order_bead_string": 32.47,
      "order_origami": 27.2,
      "order_swap_2d_puzzle": 13.71,
      "enclosure_sheep": 25.71,
      "enclosure_hole_detection": 23.75,
      "enclosure_chat_noir": 8.44,
      "knots_static": 28.59,
      "knots_untangle": 44.33,
      "Reason": 26.72,
      "Plan": 13.34
    },
    "Gemini-3.1-Flash-Lite": {
      "continuity_2d_maze": 33.76,
      "continuity_3d_maze": 36.05,
      "continuity_pipe": 0.0,
      "separation_objects": 45.73,
      "separation_one_stroke": 0.0,
      "order_bead_string": 39.76,
      "order_origami": 42.2,
      "order_swap_2d_puzzle": 11.69,
      "enclosure_sheep": 63.14,
      "enclosure_hole_detection": 31.62,
      "enclosure_chat_noir": 8.44,
      "knots_static": 71.53,
      "knots_untangle": 36.67,
      "Reason": 45.48,
      "Plan": 11.36
    },
    "Gemini-3.1-Pro": {
      "continuity_2d_maze": 36.12,
      "continuity_3d_maze": 58.27,
      "continuity_pipe": 7.33,
      "separation_objects": 53.82,
      "separation_one_stroke": 4.44,
      "order_bead_string": 51.88,
      "order_origami": 41.1,
      "order_swap_2d_puzzle": 22.47,
      "enclosure_sheep": 78.43,
      "enclosure_hole_detection": 76.11,
      "enclosure_chat_noir": 45.11,
      "knots_static": 75.29,
      "knots_untangle": 52.0,
      "Reason": 58.88,
      "Plan": 26.27
    },
    "Nemotron-Nano-12B-VL-v2": {
      "continuity_2d_maze": 14.12,
      "continuity_3d_maze": 11.82,
      "continuity_pipe": 0.0,
      "separation_objects": 28.88,
      "separation_one_stroke": 0.0,
      "order_bead_string": 20.47,
      "order_origami": 26.7,
      "order_swap_2d_puzzle": 1.57,
      "enclosure_sheep": 20.43,
      "enclosure_hole_detection": 9.87,
      "enclosure_chat_noir": 0.22,
      "knots_static": 28.35,
      "knots_untangle": 6.0,
      "Reason": 20.08,
      "Plan": 1.56
    },
    "Qwen3.5-397B-A17B": {
      "continuity_2d_maze": 14.0,
      "continuity_3d_maze": 38.65,
      "continuity_pipe": 0.0,
      "separation_objects": 44.83,
      "separation_one_stroke": 0.0,
      "order_bead_string": 21.88,
      "order_origami": 42.6,
      "order_swap_2d_puzzle": 12.36,
      "enclosure_sheep": 9.43,
      "enclosure_hole_detection": 34.91,
      "enclosure_chat_noir": 11.78,
      "knots_static": 36.59,
      "knots_untangle": 15.0,
      "Reason": 30.36,
      "Plan": 7.83
    },
    "Llama-4-Maverick-17B-128E": {
      "continuity_2d_maze": 25.65,
      "continuity_3d_maze": 17.97,
      "continuity_pipe": 0.0,
      "separation_objects": 35.73,
      "separation_one_stroke": 0.0,
      "order_bead_string": 30.94,
      "order_origami": 17.1,
      "order_swap_2d_puzzle": 7.42,
      "enclosure_sheep": 15.57,
      "enclosure_hole_detection": 3.72,
      "enclosure_chat_noir": 2.44,
      "knots_static": 35.88,
      "knots_untangle": 12.67,
      "Reason": 22.82,
      "Plan": 4.51
    },
    "Ministral-3-14B-Instruct-2512": {
      "continuity_2d_maze": 20.35,
      "continuity_3d_maze": 12.41,
      "continuity_pipe": 0.0,
      "separation_objects": 28.76,
      "separation_one_stroke": 0.0,
      "order_bead_string": 16.47,
      "order_origami": 18.4,
      "order_swap_2d_puzzle": 5.17,
      "enclosure_sheep": 16.29,
      "enclosure_hole_detection": 7.3,
      "enclosure_chat_noir": 5.33,
      "knots_static": 47.88,
      "knots_untangle": 20.67,
      "Reason": 20.98,
      "Plan": 6.23
    },
    "InternVL3.5-241B": {
      "continuity_2d_maze": 17.18,
      "continuity_3d_maze": 11.82,
      "continuity_pipe": 0.0,
      "separation_objects": 12.7,
      "separation_one_stroke": 0.0,
      "order_bead_string": 27.29,
      "order_origami": 19.5,
      "order_swap_2d_puzzle": 5.62,
      "enclosure_sheep": 22.86,
      "enclosure_hole_detection": 22.03,
      "enclosure_chat_noir": 1.33,
      "knots_static": 49.88,
      "knots_untangle": 7.33,
      "Reason": 22.91,
      "Plan": 2.86
    },
    "Gemma-4-31B-IT": {
      "continuity_2d_maze": 30.35,
      "continuity_3d_maze": 18.68,
      "continuity_pipe": 0.0,
      "separation_objects": 19.1,
      "separation_one_stroke": 0.0,
      "order_bead_string": 9.41,
      "order_origami": 1.6,
      "order_swap_2d_puzzle": 1.35,
      "enclosure_sheep": 9.29,
      "enclosure_hole_detection": 0.0,
      "enclosure_chat_noir": 17.33,
      "knots_static": 6.24,
      "knots_untangle": 19.67,
      "Reason": 11.83,
      "Plan": 7.67
    }
  }
}
