craft-leaderboard / structure_data.json
Abhijnan's picture
add structures tab with per-structure model comparison
0fd81c0
Raw
History Blame Contribute Delete
45.2 kB
[{"model": "Claude Sonnet-4.6", "structure": "structure_001", "complexity": "medium", "progress": 0.4094, "iou": 0.3074, "pos": 0.1605, "oracle": 0.8}, {"model": "Claude Sonnet-4.6", "structure": "structure_002", "complexity": "medium", "progress": 0.1186, "iou": 0.1766, "pos": 0.0, "oracle": 0.6}, {"model": "Claude Sonnet-4.6", "structure": "structure_003", "complexity": "complex", "progress": 0.0817, "iou": 0.1234, "pos": 0.0, "oracle": 0.6}, {"model": "Claude Sonnet-4.6", "structure": "structure_004", "complexity": "medium", "progress": 0.527, "iou": 0.3978, "pos": 0.2051, "oracle": 0.65}, {"model": "Claude Sonnet-4.6", "structure": "structure_005", "complexity": "medium", "progress": 0.332, "iou": 0.2778, "pos": 0.1111, "oracle": 0.5}, {"model": "Claude Sonnet-4.6", "structure": "structure_006", "complexity": "complex", "progress": 0.2137, "iou": 0.1665, "pos": 0.0769, "oracle": 0.6}, {"model": "Claude Sonnet-4.6", "structure": "structure_007", "complexity": "medium", "progress": 0.119, "iou": 0.1661, "pos": 0.0, "oracle": 0.45}, {"model": "Claude Sonnet-4.6", "structure": "structure_008", "complexity": "simple", "progress": 0.3223, "iou": 0.2533, "pos": 0.1709, "oracle": 0.5}, {"model": "Claude Sonnet-4.6", "structure": "structure_009", "complexity": "simple", "progress": 0.5061, "iou": 0.22, "pos": 0.2519, "oracle": 0.65}, {"model": "Claude Sonnet-4.6", "structure": "structure_010", "complexity": "complex", "progress": 0.4226, "iou": 0.2955, "pos": 0.0794, "oracle": 0.65}, {"model": "Claude Sonnet-4.6", "structure": "structure_011", "complexity": "simple", "progress": 0.4966, "iou": 0.2338, "pos": 0.1944, "oracle": 0.7}, {"model": "Claude Sonnet-4.6", "structure": "structure_012", "complexity": "simple", "progress": 0.5769, "iou": 0.4, "pos": 0.2222, "oracle": 1.0}, {"model": "Claude Sonnet-4.6", "structure": "structure_013", "complexity": "complex", "progress": 0.16, "iou": 0.1878, "pos": 0.0, "oracle": 0.35}, {"model": "Claude Sonnet-4.6", "structure": "structure_014", "complexity": "medium", "progress": 0.2112, "iou": 0.1635, "pos": 0.0764, "oracle": 0.65}, {"model": "Claude Sonnet-4.6", "structure": "structure_015", "complexity": "simple", "progress": 0.2738, "iou": 0.1654, "pos": 0.237, "oracle": 0.55}, {"model": "Claude Sonnet-4.6", "structure": "structure_016", "complexity": "medium", "progress": 0.1419, "iou": 0.1371, "pos": 0.0, "oracle": 0.3}, {"model": "Claude Sonnet-4.6", "structure": "structure_017", "complexity": "simple", "progress": 0.2279, "iou": 0.1647, "pos": 0.1111, "oracle": 0.6}, {"model": "Claude Sonnet-4.6", "structure": "structure_018", "complexity": "complex", "progress": 0.1228, "iou": 0.1582, "pos": 0.0, "oracle": 0.5}, {"model": "Claude Sonnet-4.6", "structure": "structure_019", "complexity": "simple", "progress": 0.1075, "iou": 0.1099, "pos": 0.2222, "oracle": 0.55}, {"model": "Claude Sonnet-4.6", "structure": "structure_020", "complexity": "medium", "progress": 0.3259, "iou": 0.2612, "pos": 0.1111, "oracle": 0.75}, {"model": "DeepSeek-V2-Lite", "structure": "structure_001", "complexity": "medium", "progress": 0.49, "iou": 0.3131, "pos": 0.1806, "oracle": 0.95}, {"model": "DeepSeek-V2-Lite", "structure": "structure_002", "complexity": "medium", "progress": 0.259, "iou": 0.2455, "pos": 0.0926, "oracle": 0.85}, {"model": "DeepSeek-V2-Lite", "structure": "structure_003", "complexity": "complex", "progress": 0.2452, "iou": 0.2246, "pos": 0.037, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_004", "complexity": "medium", "progress": 0.7005, "iou": 0.3913, "pos": 0.3077, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_005", "complexity": "medium", "progress": 0.1853, "iou": 0.1768, "pos": 0.1111, "oracle": 0.85}, {"model": "DeepSeek-V2-Lite", "structure": "structure_006", "complexity": "complex", "progress": 0.3365, "iou": 0.3701, "pos": 0.0588, "oracle": 0.95}, {"model": "DeepSeek-V2-Lite", "structure": "structure_007", "complexity": "medium", "progress": 0.1089, "iou": 0.126, "pos": 0.0, "oracle": 0.9}, {"model": "DeepSeek-V2-Lite", "structure": "structure_008", "complexity": "simple", "progress": 0.5133, "iou": 0.4412, "pos": 0.3007, "oracle": 0.85}, {"model": "DeepSeek-V2-Lite", "structure": "structure_009", "complexity": "simple", "progress": 0.3389, "iou": 0.2667, "pos": 0.2685, "oracle": 0.8333}, {"model": "DeepSeek-V2-Lite", "structure": "structure_010", "complexity": "complex", "progress": 0.3523, "iou": 0.3052, "pos": 0.0702, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_011", "complexity": "simple", "progress": 0.4887, "iou": 0.3771, "pos": 0.3037, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_012", "complexity": "simple", "progress": 0.5769, "iou": 0.4042, "pos": 0.2222, "oracle": 0.9231}, {"model": "DeepSeek-V2-Lite", "structure": "structure_013", "complexity": "complex", "progress": 0.4146, "iou": 0.3294, "pos": 0.119, "oracle": 0.9444}, {"model": "DeepSeek-V2-Lite", "structure": "structure_014", "complexity": "medium", "progress": 0.5964, "iou": 0.3623, "pos": 0.287, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_015", "complexity": "simple", "progress": 0.5284, "iou": 0.2533, "pos": 0.2828, "oracle": 0.9}, {"model": "DeepSeek-V2-Lite", "structure": "structure_016", "complexity": "medium", "progress": 0.1389, "iou": 0.1706, "pos": 0.0, "oracle": 0.9375}, {"model": "DeepSeek-V2-Lite", "structure": "structure_017", "complexity": "simple", "progress": 0.5507, "iou": 0.393, "pos": 0.2531, "oracle": 0.95}, {"model": "DeepSeek-V2-Lite", "structure": "structure_018", "complexity": "complex", "progress": 0.4121, "iou": 0.2861, "pos": 0.1528, "oracle": 1.0}, {"model": "DeepSeek-V2-Lite", "structure": "structure_019", "complexity": "simple", "progress": 0.3381, "iou": 0.1986, "pos": 0.2222, "oracle": 0.9}, {"model": "DeepSeek-V2-Lite", "structure": "structure_020", "complexity": "medium", "progress": 0.8038, "iou": 0.4489, "pos": 0.2398, "oracle": 1.0}, {"model": "Gemini 2.5-Flash", "structure": "structure_001", "complexity": "medium", "progress": 0.3777, "iou": 0.2169, "pos": 0.1605, "oracle": 0.45}, {"model": "Gemini 2.5-Flash", "structure": "structure_002", "complexity": "medium", "progress": 0.2181, "iou": 0.2, "pos": 0.0, "oracle": 0.25}, {"model": "Gemini 2.5-Flash", "structure": "structure_003", "complexity": "complex", "progress": 0.0927, "iou": 0.0978, "pos": 0.0093, "oracle": 0.35}, {"model": "Gemini 2.5-Flash", "structure": "structure_004", "complexity": "medium", "progress": 0.0927, "iou": 0.079, "pos": 0.1111, "oracle": 0.65}, {"model": "Gemini 2.5-Flash", "structure": "structure_005", "complexity": "medium", "progress": 0.5344, "iou": 0.2893, "pos": 0.1667, "oracle": 0.7}, {"model": "Gemini 2.5-Flash", "structure": "structure_006", "complexity": "complex", "progress": 0.1089, "iou": 0.0707, "pos": 0.0, "oracle": 0.3}, {"model": "Gemini 2.5-Flash", "structure": "structure_007", "complexity": "medium", "progress": 0.0938, "iou": 0.117, "pos": 0.0432, "oracle": 0.55}, {"model": "Gemini 2.5-Flash", "structure": "structure_008", "complexity": "simple", "progress": 0.2602, "iou": 0.1764, "pos": 0.2143, "oracle": 0.5}, {"model": "Gemini 2.5-Flash", "structure": "structure_009", "complexity": "simple", "progress": 0.2693, "iou": 0.175, "pos": 0.2222, "oracle": 0.5}, {"model": "Gemini 2.5-Flash", "structure": "structure_010", "complexity": "complex", "progress": 0.3304, "iou": 0.2318, "pos": 0.0778, "oracle": 0.45}, {"model": "Gemini 2.5-Flash", "structure": "structure_011", "complexity": "simple", "progress": 0.1982, "iou": 0.1076, "pos": 0.1754, "oracle": 0.65}, {"model": "Gemini 2.5-Flash", "structure": "structure_012", "complexity": "simple", "progress": 0.1961, "iou": 0.1952, "pos": 0.1111, "oracle": 0.4}, {"model": "Gemini 2.5-Flash", "structure": "structure_013", "complexity": "complex", "progress": 0.1837, "iou": 0.0643, "pos": 0.0333, "oracle": 0.9}, {"model": "Gemini 2.5-Flash", "structure": "structure_014", "complexity": "medium", "progress": 0.1222, "iou": 0.0726, "pos": 0.0427, "oracle": 0.4}, {"model": "Gemini 2.5-Flash", "structure": "structure_015", "complexity": "simple", "progress": 0.3862, "iou": 0.1521, "pos": 0.2424, "oracle": 0.55}, {"model": "Gemini 2.5-Flash", "structure": "structure_016", "complexity": "medium", "progress": 0.3011, "iou": 0.1889, "pos": 0.0131, "oracle": 0.55}, {"model": "Gemini 2.5-Flash", "structure": "structure_017", "complexity": "simple", "progress": 0.146, "iou": 0.1517, "pos": 0.1111, "oracle": 0.6}, {"model": "Gemini 2.5-Flash", "structure": "structure_018", "complexity": "complex", "progress": 0.3618, "iou": 0.2204, "pos": 0.1046, "oracle": 0.8333}, {"model": "Gemini 2.5-Flash", "structure": "structure_019", "complexity": "simple", "progress": 0.4859, "iou": 0.2262, "pos": 0.2778, "oracle": 0.5}, {"model": "Gemini 2.5-Flash", "structure": "structure_020", "complexity": "medium", "progress": 0.3904, "iou": 0.2105, "pos": 0.1111, "oracle": 0.65}, {"model": "Gemini 3-Flash", "structure": "structure_001", "complexity": "medium", "progress": 0.7353, "iou": 0.4286, "pos": 0.2698, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_002", "complexity": "medium", "progress": 0.6504, "iou": 0.3885, "pos": 0.2308, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_003", "complexity": "complex", "progress": 0.273, "iou": 0.2989, "pos": 0.0833, "oracle": 0.8333}, {"model": "Gemini 3-Flash", "structure": "structure_004", "complexity": "medium", "progress": 0.7833, "iou": 0.5165, "pos": 0.3675, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.3385, "pos": 0.2906, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_006", "complexity": "complex", "progress": 0.817, "iou": 0.5188, "pos": 0.35, "oracle": 0.9474}, {"model": "Gemini 3-Flash", "structure": "structure_007", "complexity": "medium", "progress": 0.5455, "iou": 0.4147, "pos": 0.183, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_008", "complexity": "simple", "progress": 1.0, "iou": 0.4938, "pos": 0.4097, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_009", "complexity": "simple", "progress": 1.0, "iou": 0.5113, "pos": 0.3968, "oracle": 0.875}, {"model": "Gemini 3-Flash", "structure": "structure_010", "complexity": "complex", "progress": 0.812, "iou": 0.4716, "pos": 0.2708, "oracle": 0.9444}, {"model": "Gemini 3-Flash", "structure": "structure_011", "complexity": "simple", "progress": 1.0, "iou": 0.55, "pos": 0.4306, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_012", "complexity": "simple", "progress": 0.3314, "iou": 0.2487, "pos": 0.1111, "oracle": 0.65}, {"model": "Gemini 3-Flash", "structure": "structure_013", "complexity": "complex", "progress": 0.3324, "iou": 0.2448, "pos": 0.0694, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_014", "complexity": "medium", "progress": 0.6157, "iou": 0.3658, "pos": 0.2857, "oracle": 0.9286}, {"model": "Gemini 3-Flash", "structure": "structure_015", "complexity": "simple", "progress": 1.0, "iou": 0.5902, "pos": 0.5397, "oracle": 0.9333}, {"model": "Gemini 3-Flash", "structure": "structure_016", "complexity": "medium", "progress": 0.5, "iou": 0.4107, "pos": 0.2014, "oracle": 0.8824}, {"model": "Gemini 3-Flash", "structure": "structure_017", "complexity": "simple", "progress": 0.5338, "iou": 0.4115, "pos": 0.202, "oracle": 0.95}, {"model": "Gemini 3-Flash", "structure": "structure_018", "complexity": "complex", "progress": 0.5796, "iou": 0.3409, "pos": 0.1717, "oracle": 1.0}, {"model": "Gemini 3-Flash", "structure": "structure_019", "complexity": "simple", "progress": 0.4735, "iou": 0.2901, "pos": 0.3333, "oracle": 0.95}, {"model": "Gemini 3-Flash", "structure": "structure_020", "complexity": "medium", "progress": 0.8214, "iou": 0.4395, "pos": 0.3056, "oracle": 0.9}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_001", "complexity": "medium", "progress": 0.6922, "iou": 0.3793, "pos": 0.254, "oracle": 0.7778}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_002", "complexity": "medium", "progress": 0.3545, "iou": 0.2571, "pos": 0.0794, "oracle": 0.35}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_003", "complexity": "complex", "progress": 0.1628, "iou": 0.1739, "pos": 0.0833, "oracle": 0.3}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_004", "complexity": "medium", "progress": 0.153, "iou": 0.122, "pos": 0.1111, "oracle": 1.0}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_005", "complexity": "medium", "progress": 0.4973, "iou": 0.3, "pos": 0.1515, "oracle": 0.65}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_006", "complexity": "complex", "progress": 0.0, "iou": 0.0677, "pos": 0.0, "oracle": 0.2}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_007", "complexity": "medium", "progress": 0.0, "iou": 0.0678, "pos": 0.0, "oracle": 0.3}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_008", "complexity": "simple", "progress": 0.1701, "iou": 0.1746, "pos": 0.1111, "oracle": 0.6}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_009", "complexity": "simple", "progress": 0.1392, "iou": 0.0908, "pos": 0.2222, "oracle": 0.25}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_010", "complexity": "complex", "progress": 0.3874, "iou": 0.2975, "pos": 0.0606, "oracle": 0.65}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_011", "complexity": "simple", "progress": 0.2443, "iou": 0.1621, "pos": 0.1404, "oracle": 0.9}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_012", "complexity": "simple", "progress": 0.1643, "iou": 0.15, "pos": 0.1111, "oracle": 0.15}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_013", "complexity": "complex", "progress": 0.0272, "iou": 0.05, "pos": 0.0, "oracle": 0.55}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_014", "complexity": "medium", "progress": 0.4088, "iou": 0.2088, "pos": 0.1852, "oracle": 0.6875}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_015", "complexity": "simple", "progress": 0.2412, "iou": 0.2556, "pos": 0.2222, "oracle": 0.25}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_016", "complexity": "medium", "progress": 0.1703, "iou": 0.1565, "pos": 0.0, "oracle": 0.25}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_017", "complexity": "simple", "progress": 0.0697, "iou": 0.1053, "pos": 0.1111, "oracle": 0.25}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_018", "complexity": "complex", "progress": 0.0272, "iou": 0.1389, "pos": 0.0, "oracle": 0.35}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_019", "complexity": "simple", "progress": 0.8942, "iou": 0.5259, "pos": 0.4741, "oracle": 0.95}, {"model": "Gemini 3.1-Flash-Lite", "structure": "structure_020", "complexity": "medium", "progress": 0.3311, "iou": 0.2229, "pos": 0.1438, "oracle": 0.7}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_001", "complexity": "medium", "progress": 0.5989, "iou": 0.4434, "pos": 0.2222, "oracle": 0.85}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_002", "complexity": "medium", "progress": 0.7186, "iou": 0.4634, "pos": 0.25, "oracle": 1.0}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_003", "complexity": "complex", "progress": 0.2637, "iou": 0.2558, "pos": 0.0926, "oracle": 0.9}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_004", "complexity": "medium", "progress": 0.7005, "iou": 0.3956, "pos": 0.2296, "oracle": 0.8235}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_005", "complexity": "medium", "progress": 0.3844, "iou": 0.2898, "pos": 0.1368, "oracle": 0.65}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_006", "complexity": "complex", "progress": 0.3674, "iou": 0.353, "pos": 0.1616, "oracle": 0.85}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_007", "complexity": "medium", "progress": 0.4735, "iou": 0.4144, "pos": 0.2099, "oracle": 0.95}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_008", "complexity": "simple", "progress": 0.8623, "iou": 0.5421, "pos": 0.4444, "oracle": 1.0}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_009", "complexity": "simple", "progress": 0.5915, "iou": 0.3232, "pos": 0.2727, "oracle": 1.0}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_010", "complexity": "complex", "progress": 0.812, "iou": 0.5028, "pos": 0.3889, "oracle": 1.0}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_011", "complexity": "simple", "progress": 0.6967, "iou": 0.4376, "pos": 0.2484, "oracle": 0.85}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_012", "complexity": "simple", "progress": 0.5769, "iou": 0.3958, "pos": 0.1944, "oracle": 1.0}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_013", "complexity": "complex", "progress": 0.3463, "iou": 0.2731, "pos": 0.0864, "oracle": 0.9}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_014", "complexity": "medium", "progress": 0.5964, "iou": 0.3659, "pos": 0.25, "oracle": 0.9231}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_015", "complexity": "simple", "progress": 0.8442, "iou": 0.4735, "pos": 0.4359, "oracle": 0.95}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_016", "complexity": "medium", "progress": 0.1906, "iou": 0.1494, "pos": 0.0, "oracle": 0.5714}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_017", "complexity": "simple", "progress": 0.4524, "iou": 0.3947, "pos": 0.2099, "oracle": 0.95}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_018", "complexity": "complex", "progress": 0.5796, "iou": 0.3485, "pos": 0.2626, "oracle": 0.9167}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_019", "complexity": "simple", "progress": 0.791, "iou": 0.5079, "pos": 0.4524, "oracle": 0.75}, {"model": "Gemma-2-9B-Instruct", "structure": "structure_020", "complexity": "medium", "progress": 0.7083, "iou": 0.467, "pos": 0.3111, "oracle": 1.0}, {"model": "GPT-4.1-Mini", "structure": "structure_001", "complexity": "medium", "progress": 0.4887, "iou": 0.3193, "pos": 0.2222, "oracle": 0.9333}, {"model": "GPT-4.1-Mini", "structure": "structure_002", "complexity": "medium", "progress": 0.3067, "iou": 0.2111, "pos": 0.0494, "oracle": 0.4}, {"model": "GPT-4.1-Mini", "structure": "structure_003", "complexity": "complex", "progress": 0.2137, "iou": 0.1833, "pos": 0.037, "oracle": 0.8571}, {"model": "GPT-4.1-Mini", "structure": "structure_004", "complexity": "medium", "progress": 0.259, "iou": 0.2139, "pos": 0.1111, "oracle": 0.8}, {"model": "GPT-4.1-Mini", "structure": "structure_005", "complexity": "medium", "progress": 0.5655, "iou": 0.3417, "pos": 0.237, "oracle": 0.8}, {"model": "GPT-4.1-Mini", "structure": "structure_006", "complexity": "complex", "progress": 0.1361, "iou": 0.1667, "pos": 0.0, "oracle": 0.3}, {"model": "GPT-4.1-Mini", "structure": "structure_007", "complexity": "medium", "progress": 0.2156, "iou": 0.1508, "pos": 0.0185, "oracle": 0.25}, {"model": "GPT-4.1-Mini", "structure": "structure_008", "complexity": "simple", "progress": 0.3264, "iou": 0.259, "pos": 0.1988, "oracle": 0.95}, {"model": "GPT-4.1-Mini", "structure": "structure_009", "complexity": "simple", "progress": 0.5915, "iou": 0.3182, "pos": 0.3131, "oracle": 0.6667}, {"model": "GPT-4.1-Mini", "structure": "structure_010", "complexity": "complex", "progress": 0.2318, "iou": 0.1741, "pos": 0.037, "oracle": 0.55}, {"model": "GPT-4.1-Mini", "structure": "structure_011", "complexity": "simple", "progress": 0.037, "iou": 0.0639, "pos": 0.1111, "oracle": 0.45}, {"model": "GPT-4.1-Mini", "structure": "structure_012", "complexity": "simple", "progress": 0.3552, "iou": 0.2688, "pos": 0.1111, "oracle": 0.5}, {"model": "GPT-4.1-Mini", "structure": "structure_013", "complexity": "complex", "progress": 0.0544, "iou": 0.0476, "pos": 0.0, "oracle": 0.4}, {"model": "GPT-4.1-Mini", "structure": "structure_014", "complexity": "medium", "progress": 0.5964, "iou": 0.2719, "pos": 0.2063, "oracle": 0.8571}, {"model": "GPT-4.1-Mini", "structure": "structure_015", "complexity": "simple", "progress": 0.1693, "iou": 0.0709, "pos": 0.2222, "oracle": 0.8}, {"model": "GPT-4.1-Mini", "structure": "structure_016", "complexity": "medium", "progress": 0.1419, "iou": 0.1152, "pos": 0.0, "oracle": 0.4}, {"model": "GPT-4.1-Mini", "structure": "structure_017", "complexity": "simple", "progress": 0.1351, "iou": 0.1776, "pos": 0.1111, "oracle": 0.25}, {"model": "GPT-4.1-Mini", "structure": "structure_018", "complexity": "complex", "progress": 0.1089, "iou": 0.125, "pos": 0.0, "oracle": 0.45}, {"model": "GPT-4.1-Mini", "structure": "structure_019", "complexity": "simple", "progress": 1.0, "iou": 0.5523, "pos": 0.451, "oracle": 0.85}, {"model": "GPT-4.1-Mini", "structure": "structure_020", "complexity": "medium", "progress": 0.308, "iou": 0.1684, "pos": 0.0556, "oracle": 0.45}, {"model": "GPT-4o", "structure": "structure_001", "complexity": "medium", "progress": 0.4168, "iou": 0.3, "pos": 0.1358, "oracle": 0.45}, {"model": "GPT-4o", "structure": "structure_002", "complexity": "medium", "progress": 0.7067, "iou": 0.4724, "pos": 0.3399, "oracle": 0.9412}, {"model": "GPT-4o", "structure": "structure_003", "complexity": "complex", "progress": 0.2463, "iou": 0.313, "pos": 0.0889, "oracle": 0.95}, {"model": "GPT-4o", "structure": "structure_004", "complexity": "medium", "progress": 0.7407, "iou": 0.4953, "pos": 0.2564, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.3846, "pos": 0.2564, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_006", "complexity": "complex", "progress": 0.6652, "iou": 0.4126, "pos": 0.2083, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_007", "complexity": "medium", "progress": 0.6387, "iou": 0.4103, "pos": 0.2632, "oracle": 0.95}, {"model": "GPT-4o", "structure": "structure_008", "complexity": "simple", "progress": 0.7896, "iou": 0.4688, "pos": 0.3889, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_009", "complexity": "simple", "progress": 0.9295, "iou": 0.5142, "pos": 0.3932, "oracle": 0.7}, {"model": "GPT-4o", "structure": "structure_010", "complexity": "complex", "progress": 0.4814, "iou": 0.3674, "pos": 0.1204, "oracle": 0.65}, {"model": "GPT-4o", "structure": "structure_011", "complexity": "simple", "progress": 1.0, "iou": 0.5063, "pos": 0.4167, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_012", "complexity": "simple", "progress": 0.4305, "iou": 0.3277, "pos": 0.1709, "oracle": 0.7}, {"model": "GPT-4o", "structure": "structure_013", "complexity": "complex", "progress": 0.3324, "iou": 0.2625, "pos": 0.1, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_014", "complexity": "medium", "progress": 0.162, "iou": 0.1297, "pos": 0.1, "oracle": 0.45}, {"model": "GPT-4o", "structure": "structure_015", "complexity": "simple", "progress": 0.655, "iou": 0.3746, "pos": 0.4352, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.285, "pos": 0.1235, "oracle": 1.0}, {"model": "GPT-4o", "structure": "structure_017", "complexity": "simple", "progress": 0.5186, "iou": 0.4702, "pos": 0.2444, "oracle": 0.9}, {"model": "GPT-4o", "structure": "structure_018", "complexity": "complex", "progress": 0.4044, "iou": 0.3268, "pos": 0.1778, "oracle": 0.95}, {"model": "GPT-4o", "structure": "structure_019", "complexity": "simple", "progress": 0.912, "iou": 0.6278, "pos": 0.5033, "oracle": 0.85}, {"model": "GPT-4o", "structure": "structure_020", "complexity": "medium", "progress": 0.5731, "iou": 0.3461, "pos": 0.1944, "oracle": 0.8}, {"model": "GPT-4o-Mini", "structure": "structure_001", "complexity": "medium", "progress": 0.7353, "iou": 0.4286, "pos": 0.246, "oracle": 1.0}, {"model": "GPT-4o-Mini", "structure": "structure_002", "complexity": "medium", "progress": 0.5574, "iou": 0.4517, "pos": 0.1914, "oracle": 0.9}, {"model": "GPT-4o-Mini", "structure": "structure_003", "complexity": "complex", "progress": 0.1865, "iou": 0.1464, "pos": 0.037, "oracle": 1.0}, {"model": "GPT-4o-Mini", "structure": "structure_004", "complexity": "medium", "progress": 0.4155, "iou": 0.3155, "pos": 0.2, "oracle": 1.0}, {"model": "GPT-4o-Mini", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.3808, "pos": 0.2479, "oracle": 0.9286}, {"model": "GPT-4o-Mini", "structure": "structure_006", "complexity": "complex", "progress": 0.1361, "iou": 0.1736, "pos": 0.0, "oracle": 0.3}, {"model": "GPT-4o-Mini", "structure": "structure_007", "complexity": "medium", "progress": 0.1419, "iou": 0.2432, "pos": 0.0, "oracle": 0.7}, {"model": "GPT-4o-Mini", "structure": "structure_008", "complexity": "simple", "progress": 0.4167, "iou": 0.2544, "pos": 0.2982, "oracle": 0.95}, {"model": "GPT-4o-Mini", "structure": "structure_009", "complexity": "simple", "progress": 0.2693, "iou": 0.1837, "pos": 0.2222, "oracle": 0.75}, {"model": "GPT-4o-Mini", "structure": "structure_010", "complexity": "complex", "progress": 0.2504, "iou": 0.2521, "pos": 0.0, "oracle": 0.5}, {"model": "GPT-4o-Mini", "structure": "structure_011", "complexity": "simple", "progress": 0.4584, "iou": 0.2132, "pos": 0.2143, "oracle": 0.8}, {"model": "GPT-4o-Mini", "structure": "structure_012", "complexity": "simple", "progress": 0.4153, "iou": 0.3503, "pos": 0.1508, "oracle": 0.7}, {"model": "GPT-4o-Mini", "structure": "structure_013", "complexity": "complex", "progress": 0.2548, "iou": 0.1615, "pos": 0.0278, "oracle": 0.4}, {"model": "GPT-4o-Mini", "structure": "structure_014", "complexity": "medium", "progress": 0.2454, "iou": 0.2009, "pos": 0.1042, "oracle": 0.8}, {"model": "GPT-4o-Mini", "structure": "structure_015", "complexity": "simple", "progress": 0.308, "iou": 0.2105, "pos": 0.2222, "oracle": 0.5}, {"model": "GPT-4o-Mini", "structure": "structure_016", "complexity": "medium", "progress": 0.0556, "iou": 0.0542, "pos": 0.0, "oracle": 0.3}, {"model": "GPT-4o-Mini", "structure": "structure_017", "complexity": "simple", "progress": 0.2181, "iou": 0.1974, "pos": 0.1111, "oracle": 0.25}, {"model": "GPT-4o-Mini", "structure": "structure_018", "complexity": "complex", "progress": 0.1089, "iou": 0.1369, "pos": 0.0, "oracle": 0.45}, {"model": "GPT-4o-Mini", "structure": "structure_019", "complexity": "simple", "progress": 0.3836, "iou": 0.2469, "pos": 0.2593, "oracle": 0.4}, {"model": "GPT-4o-Mini", "structure": "structure_020", "complexity": "medium", "progress": 0.3972, "iou": 0.2536, "pos": 0.1667, "oracle": 0.7}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_001", "complexity": "medium", "progress": 0.7353, "iou": 0.4429, "pos": 0.246, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_002", "complexity": "medium", "progress": 0.7186, "iou": 0.4656, "pos": 0.3056, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_003", "complexity": "complex", "progress": 0.2334, "iou": 0.2109, "pos": 0.0667, "oracle": 0.4375}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_004", "complexity": "medium", "progress": 0.1965, "iou": 0.1853, "pos": 0.1111, "oracle": 0.9}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_005", "complexity": "medium", "progress": 0.3298, "iou": 0.2681, "pos": 0.1111, "oracle": 0.5}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_006", "complexity": "complex", "progress": 0.8443, "iou": 0.5098, "pos": 0.3137, "oracle": 0.9474}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_007", "complexity": "medium", "progress": 0.7437, "iou": 0.4703, "pos": 0.2519, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_008", "complexity": "simple", "progress": 0.5269, "iou": 0.3048, "pos": 0.1905, "oracle": 0.7}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_009", "complexity": "simple", "progress": 0.5915, "iou": 0.3136, "pos": 0.2929, "oracle": 0.9167}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_010", "complexity": "complex", "progress": 0.812, "iou": 0.4858, "pos": 0.3611, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_011", "complexity": "simple", "progress": 1.0, "iou": 0.4969, "pos": 0.4722, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_012", "complexity": "simple", "progress": 0.5769, "iou": 0.3917, "pos": 0.2037, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_013", "complexity": "complex", "progress": 0.5698, "iou": 0.3632, "pos": 0.1508, "oracle": 0.7222}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_014", "complexity": "medium", "progress": 0.1187, "iou": 0.1211, "pos": 0.0915, "oracle": 0.85}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_015", "complexity": "simple", "progress": 0.7262, "iou": 0.4389, "pos": 0.3704, "oracle": 0.9}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.285, "pos": 0.0617, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_017", "complexity": "simple", "progress": 0.7211, "iou": 0.4737, "pos": 0.3248, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_018", "complexity": "complex", "progress": 0.5796, "iou": 0.3485, "pos": 0.2424, "oracle": 1.0}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_019", "complexity": "simple", "progress": 0.754, "iou": 0.5358, "pos": 0.3472, "oracle": 0.8}, {"model": "Llama-3.1-8B-Instruct", "structure": "structure_020", "complexity": "medium", "progress": 0.4981, "iou": 0.4336, "pos": 0.2667, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_001", "complexity": "medium", "progress": 0.49, "iou": 0.4063, "pos": 0.2026, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_002", "complexity": "medium", "progress": 0.49, "iou": 0.3727, "pos": 0.1966, "oracle": 0.8}, {"model": "Mistral-7B-Instruct", "structure": "structure_003", "complexity": "complex", "progress": 0.2452, "iou": 0.2101, "pos": 0.037, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_004", "complexity": "medium", "progress": 0.4813, "iou": 0.3697, "pos": 0.2, "oracle": 0.75}, {"model": "Mistral-7B-Instruct", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.4167, "pos": 0.3464, "oracle": 0.9375}, {"model": "Mistral-7B-Instruct", "structure": "structure_006", "complexity": "complex", "progress": 0.483, "iou": 0.3362, "pos": 0.1235, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_007", "complexity": "medium", "progress": 0.6521, "iou": 0.4667, "pos": 0.1704, "oracle": 0.75}, {"model": "Mistral-7B-Instruct", "structure": "structure_008", "complexity": "simple", "progress": 0.8329, "iou": 0.4425, "pos": 0.3194, "oracle": 0.8}, {"model": "Mistral-7B-Instruct", "structure": "structure_009", "complexity": "simple", "progress": 0.3907, "iou": 0.3526, "pos": 0.2333, "oracle": 0.9}, {"model": "Mistral-7B-Instruct", "structure": "structure_010", "complexity": "complex", "progress": 0.6159, "iou": 0.4515, "pos": 0.269, "oracle": 0.9}, {"model": "Mistral-7B-Instruct", "structure": "structure_011", "complexity": "simple", "progress": 1.0, "iou": 0.5438, "pos": 0.4792, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_012", "complexity": "simple", "progress": 0.4241, "iou": 0.3792, "pos": 0.1667, "oracle": 0.6}, {"model": "Mistral-7B-Instruct", "structure": "structure_013", "complexity": "complex", "progress": 0.3463, "iou": 0.2602, "pos": 0.101, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_014", "complexity": "medium", "progress": 0.6157, "iou": 0.3813, "pos": 0.1825, "oracle": 0.9286}, {"model": "Mistral-7B-Instruct", "structure": "structure_015", "complexity": "simple", "progress": 1.0, "iou": 0.5977, "pos": 0.5556, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.3043, "pos": 0.0988, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_017", "complexity": "simple", "progress": 1.0, "iou": 0.5789, "pos": 0.4222, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_018", "complexity": "complex", "progress": 0.6074, "iou": 0.3576, "pos": 0.213, "oracle": 0.9474}, {"model": "Mistral-7B-Instruct", "structure": "structure_019", "complexity": "simple", "progress": 0.9841, "iou": 0.5926, "pos": 0.4877, "oracle": 1.0}, {"model": "Mistral-7B-Instruct", "structure": "structure_020", "complexity": "medium", "progress": 0.8038, "iou": 0.4551, "pos": 0.3007, "oracle": 0.9444}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_001", "complexity": "medium", "progress": 0.1889, "iou": 0.2063, "pos": 0.1111, "oracle": 0.65}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_002", "complexity": "medium", "progress": 0.4201, "iou": 0.2864, "pos": 0.1966, "oracle": 0.9167}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_003", "complexity": "complex", "progress": 0.1895, "iou": 0.2327, "pos": 0.098, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_004", "complexity": "medium", "progress": 0.548, "iou": 0.3489, "pos": 0.2626, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_005", "complexity": "medium", "progress": 0.1426, "iou": 0.1104, "pos": 0.1111, "oracle": 0.6}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_006", "complexity": "complex", "progress": 0.08, "iou": 0.1043, "pos": 0.0, "oracle": 0.25}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_007", "complexity": "medium", "progress": 0.7857, "iou": 0.5218, "pos": 0.2157, "oracle": 0.9474}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_008", "complexity": "simple", "progress": 1.0, "iou": 0.5281, "pos": 0.3889, "oracle": 0.9412}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_009", "complexity": "simple", "progress": 1.0, "iou": 0.5113, "pos": 0.373, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_010", "complexity": "complex", "progress": 0.7331, "iou": 0.3961, "pos": 0.1746, "oracle": 0.85}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_011", "complexity": "simple", "progress": 0.8305, "iou": 0.4286, "pos": 0.4048, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_012", "complexity": "simple", "progress": 0.3745, "iou": 0.2167, "pos": 0.1778, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_013", "complexity": "complex", "progress": 0.3324, "iou": 0.2344, "pos": 0.0833, "oracle": 0.6316}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_014", "complexity": "medium", "progress": 0.1789, "iou": 0.1304, "pos": 0.0833, "oracle": 0.2}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_015", "complexity": "simple", "progress": 0.5157, "iou": 0.3158, "pos": 0.3016, "oracle": 0.55}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.285, "pos": 0.1235, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_017", "complexity": "simple", "progress": 0.3859, "iou": 0.2982, "pos": 0.1852, "oracle": 0.3}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_018", "complexity": "complex", "progress": 0.2133, "iou": 0.2503, "pos": 0.0, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_019", "complexity": "simple", "progress": 0.6111, "iou": 0.4236, "pos": 0.2986, "oracle": 0.75}, {"model": "Qwen2.5-Instruct-14B", "structure": "structure_020", "complexity": "medium", "progress": 0.5356, "iou": 0.3711, "pos": 0.2056, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_001", "complexity": "medium", "progress": 0.485, "iou": 0.3893, "pos": 0.2063, "oracle": 0.6}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_002", "complexity": "medium", "progress": 0.1246, "iou": 0.15, "pos": 0.0, "oracle": 0.2}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_003", "complexity": "complex", "progress": 0.2137, "iou": 0.1562, "pos": 0.0556, "oracle": 0.875}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_004", "complexity": "medium", "progress": 0.211, "iou": 0.1252, "pos": 0.1111, "oracle": 0.4}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.3731, "pos": 0.2222, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_006", "complexity": "complex", "progress": 0.2178, "iou": 0.1061, "pos": 0.0, "oracle": 0.4}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_007", "complexity": "medium", "progress": 0.5606, "iou": 0.4431, "pos": 0.1282, "oracle": 0.7}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_008", "complexity": "simple", "progress": 0.7783, "iou": 0.4308, "pos": 0.2479, "oracle": 0.8}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_009", "complexity": "simple", "progress": 0.5915, "iou": 0.3139, "pos": 0.2929, "oracle": 0.7333}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_010", "complexity": "complex", "progress": 0.3802, "iou": 0.2722, "pos": 0.0296, "oracle": 0.65}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_011", "complexity": "simple", "progress": 0.1795, "iou": 0.1581, "pos": 0.1111, "oracle": 0.4}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_012", "complexity": "simple", "progress": 0.4815, "iou": 0.2551, "pos": 0.1852, "oracle": 0.8824}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_013", "complexity": "complex", "progress": 0.2276, "iou": 0.175, "pos": 0.0444, "oracle": 0.3}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_014", "complexity": "medium", "progress": 0.1928, "iou": 0.1335, "pos": 0.0741, "oracle": 0.45}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_015", "complexity": "simple", "progress": 0.1075, "iou": 0.0526, "pos": 0.2222, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.2899, "pos": 0.1358, "oracle": 0.8333}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_017", "complexity": "simple", "progress": 0.2968, "iou": 0.1778, "pos": 0.1313, "oracle": 0.6}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_018", "complexity": "complex", "progress": 0.1906, "iou": 0.1759, "pos": 0.0, "oracle": 0.35}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_019", "complexity": "simple", "progress": 0.2448, "iou": 0.1319, "pos": 0.2444, "oracle": 0.4}, {"model": "Qwen2.5-Instruct-32B", "structure": "structure_020", "complexity": "medium", "progress": 0.1454, "iou": 0.0915, "pos": 0.1046, "oracle": 0.65}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_001", "complexity": "medium", "progress": 0.7353, "iou": 0.4286, "pos": 0.2619, "oracle": 0.8947}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_002", "complexity": "medium", "progress": 0.6504, "iou": 0.4038, "pos": 0.2051, "oracle": 0.9286}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_003", "complexity": "complex", "progress": 0.2276, "iou": 0.2546, "pos": 0.0963, "oracle": 0.7}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_004", "complexity": "medium", "progress": 0.3349, "iou": 0.2064, "pos": 0.1319, "oracle": 0.9}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_005", "complexity": "medium", "progress": 0.361, "iou": 0.29, "pos": 0.1111, "oracle": 0.6}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_006", "complexity": "complex", "progress": 0.78, "iou": 0.5352, "pos": 0.3272, "oracle": 0.9}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_007", "complexity": "medium", "progress": 0.3287, "iou": 0.2153, "pos": 0.0256, "oracle": 0.8}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_008", "complexity": "simple", "progress": 0.7525, "iou": 0.406, "pos": 0.3254, "oracle": 0.7}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_009", "complexity": "simple", "progress": 0.5984, "iou": 0.3632, "pos": 0.2667, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_010", "complexity": "complex", "progress": 0.5154, "iou": 0.3485, "pos": 0.1975, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_011", "complexity": "simple", "progress": 0.6662, "iou": 0.425, "pos": 0.3472, "oracle": 0.7}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_012", "complexity": "simple", "progress": 0.3473, "iou": 0.3006, "pos": 0.1111, "oracle": 0.55}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_013", "complexity": "complex", "progress": 0.3324, "iou": 0.25, "pos": 0.0694, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_014", "complexity": "medium", "progress": 0.5964, "iou": 0.3732, "pos": 0.2778, "oracle": 0.8}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_015", "complexity": "simple", "progress": 0.6444, "iou": 0.3136, "pos": 0.3434, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_016", "complexity": "medium", "progress": 0.1944, "iou": 0.1896, "pos": 0.0, "oracle": 0.5263}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_017", "complexity": "simple", "progress": 1.0, "iou": 0.593, "pos": 0.4074, "oracle": 0.9412}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_018", "complexity": "complex", "progress": 0.5796, "iou": 0.3295, "pos": 0.1717, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_019", "complexity": "simple", "progress": 0.8624, "iou": 0.537, "pos": 0.3926, "oracle": 0.7}, {"model": "Qwen2.5-Instruct-72B", "structure": "structure_020", "complexity": "medium", "progress": 0.6269, "iou": 0.3769, "pos": 0.2026, "oracle": 0.9}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_001", "complexity": "medium", "progress": 0.3865, "iou": 0.2949, "pos": 0.1852, "oracle": 0.9}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_002", "complexity": "medium", "progress": 0.7186, "iou": 0.4214, "pos": 0.2857, "oracle": 0.875}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_003", "complexity": "complex", "progress": 0.2452, "iou": 0.2348, "pos": 0.0667, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_004", "complexity": "medium", "progress": 0.548, "iou": 0.3686, "pos": 0.246, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_005", "complexity": "medium", "progress": 0.7019, "iou": 0.3808, "pos": 0.2906, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_006", "complexity": "complex", "progress": 0.6015, "iou": 0.3787, "pos": 0.1111, "oracle": 0.65}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_007", "complexity": "medium", "progress": 0.6521, "iou": 0.4603, "pos": 0.1185, "oracle": 0.75}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_008", "complexity": "simple", "progress": 0.7677, "iou": 0.5112, "pos": 0.3684, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_009", "complexity": "simple", "progress": 1.0, "iou": 0.5113, "pos": 0.3968, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_010", "complexity": "complex", "progress": 0.5655, "iou": 0.4731, "pos": 0.2667, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_011", "complexity": "simple", "progress": 0.6869, "iou": 0.4137, "pos": 0.3684, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_012", "complexity": "simple", "progress": 0.5769, "iou": 0.4049, "pos": 0.2381, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_013", "complexity": "complex", "progress": 0.3228, "iou": 0.2561, "pos": 0.1111, "oracle": 0.9}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_014", "complexity": "medium", "progress": 0.6157, "iou": 0.372, "pos": 0.2381, "oracle": 0.8571}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_015", "complexity": "simple", "progress": 1.0, "iou": 0.5752, "pos": 0.4762, "oracle": 0.9375}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_016", "complexity": "medium", "progress": 0.4517, "iou": 0.3041, "pos": 0.0684, "oracle": 1.0}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_017", "complexity": "simple", "progress": 0.5921, "iou": 0.3831, "pos": 0.1944, "oracle": 0.65}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_018", "complexity": "complex", "progress": 0.817, "iou": 0.4301, "pos": 0.2353, "oracle": 0.9412}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_019", "complexity": "simple", "progress": 0.4946, "iou": 0.3983, "pos": 0.2654, "oracle": 0.85}, {"model": "Qwen2.5-Instruct-7B", "structure": "structure_020", "complexity": "medium", "progress": 0.5022, "iou": 0.4632, "pos": 0.1944, "oracle": 1.0}]