WebCoderBench / src /unweighted_z_score.json
doubao-bench's picture
update data
4466f70
Raw
History Blame Contribute Delete
19.7 kB
[
{
"ID": 1,
"Model": "DeepSeek-R1-0528",
"Code Quality": {
"General Functionality Correctness": -0.3699,
"Best Practices": 0.1256,
"Error Handling": 0.1622,
"Runtime Console Errors": 0.0938,
"Static Syntax Checking (Linting)": 0.1041
},
"Visual Quality": {
"General Visual Experience": -0.3956,
"Component Style Consistency": -0.047,
"Icon Style Consistency": -0.5862,
"Layout Consistency": -0.0533,
"Layout Sparsity": 0.2614,
"Visual Harmony Degree": 0.1952
},
"Content Quality": {
"Copywriting Quality": -0.0512,
"Media Quality": 0.1059,
"Placeholder Quality": 0.0128,
"Resource Validity": 0.4508
},
"Performance Quality": {
"General Performance": 0.0248
},
"Accessbility": {
"Accessibility Core Metrics": 0.1433,
"Cross-Browser Compatibility": 0.1725,
"Mobile Device Compatibility": 0.1076
},
"Maintainability": {
"Code Redundancy Rate": 0.0422,
"Comment Rate": 0.1701
},
"Alignment": {
"Functional Alignment": -0.0697,
"Visual Alignment": 0.0219,
"Content Alignment": 0.0195
}
},
{
"ID": 2,
"Model": "DeepSeek-V3.1",
"Code Quality": {
"General Functionality Correctness": -0.4223,
"Best Practices": 0.1158,
"Error Handling": 0.1518,
"Runtime Console Errors": -0.0284,
"Static Syntax Checking (Linting)": 0.0602
},
"Visual Quality": {
"General Visual Experience": -0.8833,
"Component Style Consistency": 0.0801,
"Icon Style Consistency": 0.2612,
"Layout Consistency": 0.0505,
"Layout Sparsity": -0.0731,
"Visual Harmony Degree": 0.0427
},
"Content Quality": {
"Copywriting Quality": -0.0097,
"Media Quality": -0.0654,
"Placeholder Quality": -0.1864,
"Resource Validity": -0.1057
},
"Performance Quality": {
"General Performance": 0.0718
},
"Accessbility": {
"Accessibility Core Metrics": -0.0806,
"Cross-Browser Compatibility": -0.2108,
"Mobile Device Compatibility": -0.1006
},
"Maintainability": {
"Code Redundancy Rate": 0.0593,
"Comment Rate": -0.0553
},
"Alignment": {
"Functional Alignment": -0.0001,
"Visual Alignment": 0.0368,
"Content Alignment": -0.0252
}
},
{
"ID": 3,
"Model": "DeepSeek-V3.1-Terminus",
"Code Quality": {
"General Functionality Correctness": -0.2846,
"Best Practices": 0.1971,
"Error Handling": 0.0791,
"Runtime Console Errors": 0.1495,
"Static Syntax Checking (Linting)": 0.106
},
"Visual Quality": {
"General Visual Experience": 0.7438,
"Component Style Consistency": 0.0655,
"Icon Style Consistency": -0.2315,
"Layout Consistency": 0.035,
"Layout Sparsity": 0.2399,
"Visual Harmony Degree": 0.1721
},
"Content Quality": {
"Copywriting Quality": -0.0305,
"Media Quality": -0.5671,
"Placeholder Quality": -0.147,
"Resource Validity": 0.1044
},
"Performance Quality": {
"General Performance": 0.1203
},
"Accessbility": {
"Accessibility Core Metrics": 0.1017,
"Cross-Browser Compatibility": 0.155,
"Mobile Device Compatibility": 0.093
},
"Maintainability": {
"Code Redundancy Rate": 0.1273,
"Comment Rate": 0.3809
},
"Alignment": {
"Functional Alignment": 0.0369,
"Visual Alignment": -0.0029,
"Content Alignment": 0.0024
}
},
{
"ID": 4,
"Model": "DeepSeek-V3.1-Thinking",
"Code Quality": {
"General Functionality Correctness": -0.4038,
"Best Practices": 0.1054,
"Error Handling": 0.1582,
"Runtime Console Errors": -0.0948,
"Static Syntax Checking (Linting)": 0.0385
},
"Visual Quality": {
"General Visual Experience": -0.8668,
"Component Style Consistency": 0.0488,
"Icon Style Consistency": 0.2901,
"Layout Consistency": 0.0781,
"Layout Sparsity": -0.0606,
"Visual Harmony Degree": 0.049
},
"Content Quality": {
"Copywriting Quality": -0.0133,
"Media Quality": 0.126,
"Placeholder Quality": -0.1942,
"Resource Validity": -0.0728
},
"Performance Quality": {
"General Performance": 0.1027
},
"Accessbility": {
"Accessibility Core Metrics": -0.0838,
"Cross-Browser Compatibility": -0.1078,
"Mobile Device Compatibility": -0.1274
},
"Maintainability": {
"Code Redundancy Rate": 0.076,
"Comment Rate": -0.068
},
"Alignment": {
"Functional Alignment": -0.0098,
"Visual Alignment": -0.0252,
"Content Alignment": -0.0395
}
},
{
"ID": 5,
"Model": "GLM-4.5",
"Code Quality": {
"General Functionality Correctness": -0.208,
"Best Practices": 0.1642,
"Error Handling": -0.0181,
"Runtime Console Errors": 0.2018,
"Static Syntax Checking (Linting)": 0.108
},
"Visual Quality": {
"General Visual Experience": 0.78,
"Component Style Consistency": 0.0864,
"Icon Style Consistency": 0.0392,
"Layout Consistency": 0.0327,
"Layout Sparsity": 0.1503,
"Visual Harmony Degree": 0.078
},
"Content Quality": {
"Copywriting Quality": -0.0276,
"Media Quality": 0.8704,
"Placeholder Quality": 0.2424,
"Resource Validity": 0.6038
},
"Performance Quality": {
"General Performance": 0.0404
},
"Accessbility": {
"Accessibility Core Metrics": -0.0311,
"Cross-Browser Compatibility": 0.2128,
"Mobile Device Compatibility": -0.0587
},
"Maintainability": {
"Code Redundancy Rate": 0.0725,
"Comment Rate": 0.0558
},
"Alignment": {
"Functional Alignment": 0.1122,
"Visual Alignment": 0.0885,
"Content Alignment": 0.0361
}
},
{
"ID": 6,
"Model": "Qwen3-Coder-Plus",
"Code Quality": {
"General Functionality Correctness": -0.355,
"Best Practices": -0.0543,
"Error Handling": 0.1874,
"Runtime Console Errors": 0.1608,
"Static Syntax Checking (Linting)": 0.0849
},
"Visual Quality": {
"General Visual Experience": -0.6834,
"Component Style Consistency": 0.1364,
"Icon Style Consistency": -0.4843,
"Layout Consistency": 0.0737,
"Layout Sparsity": 0.1757,
"Visual Harmony Degree": 0.0451
},
"Content Quality": {
"Copywriting Quality": 0.0008,
"Media Quality": -0.3977,
"Placeholder Quality": -0.0472,
"Resource Validity": 0.2005
},
"Performance Quality": {
"General Performance": 0.1492
},
"Accessbility": {
"Accessibility Core Metrics": 0.1679,
"Cross-Browser Compatibility": -0.0163,
"Mobile Device Compatibility": 0.0883
},
"Maintainability": {
"Code Redundancy Rate": 0.1934,
"Comment Rate": 0.1257
},
"Alignment": {
"Functional Alignment": -0.1105,
"Visual Alignment": -0.1105,
"Content Alignment": -0.0861
}
},
{
"ID": 7,
"Model": "Qwen3-235B-A22B-Instruct",
"Code Quality": {
"General Functionality Correctness": -0.2647,
"Best Practices": -0.1941,
"Error Handling": 0.1561,
"Runtime Console Errors": -0.0488,
"Static Syntax Checking (Linting)": -0.0281
},
"Visual Quality": {
"General Visual Experience": 0.2797,
"Component Style Consistency": 0.123,
"Icon Style Consistency": -0.3037,
"Layout Consistency": 0.143,
"Layout Sparsity": -0.148,
"Visual Harmony Degree": -0.1542
},
"Content Quality": {
"Copywriting Quality": 0.0517,
"Media Quality": -0.0613,
"Placeholder Quality": -0.0344,
"Resource Validity": -0.1425
},
"Performance Quality": {
"General Performance": 0.0599
},
"Accessbility": {
"Accessibility Core Metrics": 0.0006,
"Cross-Browser Compatibility": -0.1347,
"Mobile Device Compatibility": 0.1377
},
"Maintainability": {
"Code Redundancy Rate": 0.1295,
"Comment Rate": -0.0049
},
"Alignment": {
"Functional Alignment": -0.0037,
"Visual Alignment": -0.0006,
"Content Alignment": 0.0196
}
},
{
"ID": 8,
"Model": "MiniMax-M2",
"Code Quality": {
"General Functionality Correctness": 0.586,
"Best Practices": 0.0799,
"Error Handling": -0.4363,
"Runtime Console Errors": 0.0143,
"Static Syntax Checking (Linting)": -0.2846
},
"Visual Quality": {
"General Visual Experience": -0.3207,
"Component Style Consistency": -0.2503,
"Icon Style Consistency": 0.0883,
"Layout Consistency": 0.0294,
"Layout Sparsity": -0.0894,
"Visual Harmony Degree": 0.1052
},
"Content Quality": {
"Copywriting Quality": 0.0234,
"Media Quality": -0.5651,
"Placeholder Quality": 0.1595,
"Resource Validity": 0.1304
},
"Performance Quality": {
"General Performance": 0.0355
},
"Accessbility": {
"Accessibility Core Metrics": -0.2779,
"Cross-Browser Compatibility": 0.1584,
"Mobile Device Compatibility": -0.1204
},
"Maintainability": {
"Code Redundancy Rate": -0.0715,
"Comment Rate": 0.4824
},
"Alignment": {
"Functional Alignment": 0.2272,
"Visual Alignment": 0.1584,
"Content Alignment": 0.1541
}
},
{
"ID": 9,
"Model": "Gemini-2.5-Pro",
"Code Quality": {
"General Functionality Correctness": 0.3541,
"Best Practices": -0.1512,
"Error Handling": 0.0824,
"Runtime Console Errors": -0.0155,
"Static Syntax Checking (Linting)": -0.0445
},
"Visual Quality": {
"General Visual Experience": 0.4479,
"Component Style Consistency": -0.0888,
"Icon Style Consistency": 0.5616,
"Layout Consistency": -0.1118,
"Layout Sparsity": -0.217,
"Visual Harmony Degree": -0.1729
},
"Content Quality": {
"Copywriting Quality": 0.0612,
"Media Quality": -0.2556,
"Placeholder Quality": 0.1294,
"Resource Validity": -0.0244
},
"Performance Quality": {
"General Performance": -0.1978
},
"Accessbility": {
"Accessibility Core Metrics": 0.0667,
"Cross-Browser Compatibility": 0.1441,
"Mobile Device Compatibility": -0.0633
},
"Maintainability": {
"Code Redundancy Rate": -0.1404,
"Comment Rate": -0.2124
},
"Alignment": {
"Functional Alignment": 0.0645,
"Visual Alignment": 0.1077,
"Content Alignment": 0.0302
}
},
{
"ID": 10,
"Model": "GPT-4o-2024-11-20",
"Code Quality": {
"General Functionality Correctness": -0.6459,
"Best Practices": 0.0849,
"Error Handling": 0.3867,
"Runtime Console Errors": -0.3998,
"Static Syntax Checking (Linting)": 0.1112
},
"Visual Quality": {
"General Visual Experience": -0.2261,
"Component Style Consistency": 0.2475,
"Icon Style Consistency": -0.4843,
"Layout Consistency": 0.135,
"Layout Sparsity": -0.6292,
"Visual Harmony Degree": -0.3277
},
"Content Quality": {
"Copywriting Quality": 0.1031,
"Media Quality": -0.2531,
"Placeholder Quality": 0.1347,
"Resource Validity": -0.5137
},
"Performance Quality": {
"General Performance": -0.2183
},
"Accessbility": {
"Accessibility Core Metrics": 0.2383,
"Cross-Browser Compatibility": -0.725,
"Mobile Device Compatibility": 0.1246
},
"Maintainability": {
"Code Redundancy Rate": -0.047,
"Comment Rate": -0.968
},
"Alignment": {
"Functional Alignment": -0.7851,
"Visual Alignment": -0.7003,
"Content Alignment": -0.5588
}
},
{
"ID": 11,
"Model": "GPT-5-Codex-High",
"Code Quality": {
"General Functionality Correctness": 0.6954,
"Best Practices": -0.6779,
"Error Handling": -0.1503,
"Runtime Console Errors": 0.1408,
"Static Syntax Checking (Linting)": -0.0671
},
"Visual Quality": {
"General Visual Experience": 1.008,
"Component Style Consistency": 0.0008,
"Icon Style Consistency": 0.1264,
"Layout Consistency": -0.2603,
"Layout Sparsity": 0.2346,
"Visual Harmony Degree": -0.0971
},
"Content Quality": {
"Copywriting Quality": -0.0988,
"Media Quality": -0.2587,
"Placeholder Quality": 0.1573,
"Resource Validity": -0.1401
},
"Performance Quality": {
"General Performance": -0.1876
},
"Accessbility": {
"Accessibility Core Metrics": 0.2241,
"Cross-Browser Compatibility": 0.095,
"Mobile Device Compatibility": 0.1973
},
"Maintainability": {
"Code Redundancy Rate": -0.1243,
"Comment Rate": -1.3085
},
"Alignment": {
"Functional Alignment": 0.1495,
"Visual Alignment": 0.1899,
"Content Alignment": 0.1874
}
},
{
"ID": 12,
"Model": "GPT-5-High",
"Code Quality": {
"General Functionality Correctness": 0.9259,
"Best Practices": 0.1093,
"Error Handling": -0.673,
"Runtime Console Errors": 0.0981,
"Static Syntax Checking (Linting)": -0.2977
},
"Visual Quality": {
"General Visual Experience": 0.8959,
"Component Style Consistency": -0.2097,
"Icon Style Consistency": -0.2034,
"Layout Consistency": -0.2432,
"Layout Sparsity": 0.0554,
"Visual Harmony Degree": 0.079
},
"Content Quality": {
"Copywriting Quality": -0.0662,
"Media Quality": -0.5889,
"Placeholder Quality": 0.1692,
"Resource Validity": 0.0545
},
"Performance Quality": {
"General Performance": 0.1114
},
"Accessbility": {
"Accessibility Core Metrics": -0.4192,
"Cross-Browser Compatibility": 0.2234,
"Mobile Device Compatibility": -0.2856
},
"Maintainability": {
"Code Redundancy Rate": -0.2415,
"Comment Rate": 0.3605
},
"Alignment": {
"Functional Alignment": 0.3915,
"Visual Alignment": 0.2497,
"Content Alignment": 0.2745
}
},
{
"ID": 13,
"Model": "Manus",
"Code Quality": {
"General Functionality Correctness": 0.2278,
"Best Practices": -0.0221,
"Error Handling": -0.1865,
"Runtime Console Errors": -0.2492,
"Static Syntax Checking (Linting)": 0.2409
},
"Visual Quality": {
"General Visual Experience": -0.4364,
"Component Style Consistency": 0.2511,
"Icon Style Consistency": -0.1441,
"Layout Consistency": 0.0068,
"Layout Sparsity": 0.0733,
"Visual Harmony Degree": -0.0144
},
"Content Quality": {
"Copywriting Quality": -0.0222,
"Media Quality": -0.077,
"Placeholder Quality": 0.0752,
"Resource Validity": 0.2568
},
"Performance Quality": {
"General Performance": -0.049
},
"Accessbility": {
"Accessibility Core Metrics": -0.031,
"Cross-Browser Compatibility": -0.4325,
"Mobile Device Compatibility": 0.0352
},
"Maintainability": {
"Code Redundancy Rate": -0.2326,
"Comment Rate": 0.4846
},
"Alignment": {
"Functional Alignment": 0.2342,
"Visual Alignment": 0.0348,
"Content Alignment": 0.0985
}
},
{
"ID": 14,
"Model": "MiniMax Agent",
"Code Quality": {
"General Functionality Correctness": -0.0796,
"Best Practices": 0.1917,
"Error Handling": -0.2998,
"Runtime Console Errors": -0.1372,
"Static Syntax Checking (Linting)": 0.2409
},
"Visual Quality": {
"General Visual Experience": -0.5171,
"Component Style Consistency": -0.4619,
"Icon Style Consistency": -0.4263,
"Layout Consistency": 0.0195,
"Layout Sparsity": -0.0248,
"Visual Harmony Degree": -0.0166
},
"Content Quality": {
"Copywriting Quality": -0.1069,
"Media Quality": 1.3456,
"Placeholder Quality": 0.2398,
"Resource Validity": 0.668
},
"Performance Quality": {
"General Performance": -0.1217
},
"Accessbility": {
"Accessibility Core Metrics": -0.0239,
"Cross-Browser Compatibility": -0.6377,
"Mobile Device Compatibility": 0.0761
},
"Maintainability": {
"Code Redundancy Rate": -0.4752,
"Comment Rate": 0.5712
},
"Alignment": {
"Functional Alignment": 0.1215,
"Visual Alignment": 0.0812,
"Content Alignment": 0.002
}
}
]