WebCoderBench / src /weighted_z_score.json
doubao-bench's picture
update data
4466f70
Raw
History Blame Contribute Delete
22.1 kB
[
{
"ID": 1,
"Model": "DeepSeek-R1-0528",
"Code Quality": {
"General Functionality Correctness": -0.01335339,
"Best Practices": 0.00373032,
"Error Handling": 0.0030818,
"Runtime Console Errors": 0.0019229,
"Static Syntax Checking (Linting)": 0.00154068
},
"Visual Quality": {
"General Visual Experience": -0.00933616,
"Component Style Consistency": -0.0006909,
"Icon Style Consistency": -0.00721026,
"Layout Consistency": -0.00078884,
"Layout Sparsity": 0.00297996,
"Visual Harmony Degree": 0.00242048
},
"Content Quality": {
"Copywriting Quality": -0.00165376,
"Media Quality": 0.00281694,
"Placeholder Quality": 0.00030848,
"Resource Validity": 0.01658944
},
"Performance Quality": {
"General Performance": 0.00282472
},
"Accessbility": {
"Accessibility Core Metrics": 0.00500117,
"Cross-Browser Compatibility": 0.0041055,
"Mobile Device Compatibility": 0.0041964
},
"Maintainability": {
"Code Redundancy Rate": 0.00181882,
"Comment Rate": 0.00908334
},
"Alignment": {
"Functional Alignment": -0.00980679,
"Visual Alignment": 0.00207174,
"Content Alignment": 0.00248625
},
"Overall Score": {
"Overall Score": 0.02413884
}
},
{
"ID": 2,
"Model": "DeepSeek-V3.1",
"Code Quality": {
"General Functionality Correctness": -0.01524503,
"Best Practices": 0.00343926,
"Error Handling": 0.0028842,
"Runtime Console Errors": -0.0005822,
"Static Syntax Checking (Linting)": 0.00089096
},
"Visual Quality": {
"General Visual Experience": -0.02084588,
"Component Style Consistency": 0.00117747,
"Icon Style Consistency": 0.00321276,
"Layout Consistency": 0.0007474,
"Layout Sparsity": -0.00083334,
"Visual Harmony Degree": 0.00052948
},
"Content Quality": {
"Copywriting Quality": -0.00031331,
"Media Quality": -0.00173964,
"Placeholder Quality": -0.00449224,
"Resource Validity": -0.00388976
},
"Performance Quality": {
"General Performance": 0.00817802
},
"Accessbility": {
"Accessibility Core Metrics": -0.00281294,
"Cross-Browser Compatibility": -0.00501704,
"Mobile Device Compatibility": -0.0039234
},
"Maintainability": {
"Code Redundancy Rate": 0.00255583,
"Comment Rate": -0.00295302
},
"Alignment": {
"Functional Alignment": -1.407e-05,
"Visual Alignment": 0.00348128,
"Content Alignment": -0.003213
},
"Overall Score": {
"Overall Score": -0.03877821
}
},
{
"ID": 3,
"Model": "DeepSeek-V3.1-Terminus",
"Code Quality": {
"General Functionality Correctness": -0.01027406,
"Best Practices": 0.00585387,
"Error Handling": 0.0015029,
"Runtime Console Errors": 0.00306475,
"Static Syntax Checking (Linting)": 0.0015688
},
"Visual Quality": {
"General Visual Experience": 0.01755368,
"Component Style Consistency": 0.00096285,
"Icon Style Consistency": -0.00284745,
"Layout Consistency": 0.000518,
"Layout Sparsity": 0.00273486,
"Visual Harmony Degree": 0.00213404
},
"Content Quality": {
"Copywriting Quality": -0.00098515,
"Media Quality": -0.01508486,
"Placeholder Quality": -0.0035427,
"Resource Validity": 0.00384192
},
"Performance Quality": {
"General Performance": 0.01370217
},
"Accessbility": {
"Accessibility Core Metrics": 0.00354933,
"Cross-Browser Compatibility": 0.003689,
"Mobile Device Compatibility": 0.003627
},
"Maintainability": {
"Code Redundancy Rate": 0.00548663,
"Comment Rate": 0.02034006
},
"Alignment": {
"Functional Alignment": 0.00519183,
"Visual Alignment": -0.00027434,
"Content Alignment": 0.000306
},
"Overall Score": {
"Overall Score": 0.06261913
}
},
{
"ID": 4,
"Model": "DeepSeek-V3.1-Thinking",
"Code Quality": {
"General Functionality Correctness": -0.01457718,
"Best Practices": 0.00313038,
"Error Handling": 0.0030058,
"Runtime Console Errors": -0.0019434,
"Static Syntax Checking (Linting)": 0.0005698
},
"Visual Quality": {
"General Visual Experience": -0.02045648,
"Component Style Consistency": 0.00071736,
"Icon Style Consistency": 0.00356823,
"Layout Consistency": 0.00115588,
"Layout Sparsity": -0.00069084,
"Visual Harmony Degree": 0.0006076
},
"Content Quality": {
"Copywriting Quality": -0.00042959,
"Media Quality": 0.0033516,
"Placeholder Quality": -0.00468022,
"Resource Validity": -0.00267904
},
"Performance Quality": {
"General Performance": 0.01169753
},
"Accessbility": {
"Accessibility Core Metrics": -0.00292462,
"Cross-Browser Compatibility": -0.00256564,
"Mobile Device Compatibility": -0.0049686
},
"Maintainability": {
"Code Redundancy Rate": 0.0032756,
"Comment Rate": -0.0036312
},
"Alignment": {
"Functional Alignment": -0.00137886,
"Visual Alignment": -0.00238392,
"Content Alignment": -0.00503625
},
"Overall Score": {
"Overall Score": -0.03726606
}
},
{
"ID": 5,
"Model": "GLM-4.5",
"Code Quality": {
"General Functionality Correctness": -0.0075088,
"Best Practices": 0.00487674,
"Error Handling": -0.0003439,
"Runtime Console Errors": 0.0041369,
"Static Syntax Checking (Linting)": 0.0015984
},
"Visual Quality": {
"General Visual Experience": 0.018408,
"Component Style Consistency": 0.00127008,
"Icon Style Consistency": 0.00048216,
"Layout Consistency": 0.00048396,
"Layout Sparsity": 0.00171342,
"Visual Harmony Degree": 0.0009672
},
"Content Quality": {
"Copywriting Quality": -0.00089148,
"Media Quality": 0.02315264,
"Placeholder Quality": 0.00584184,
"Resource Validity": 0.02221984
},
"Performance Quality": {
"General Performance": 0.00460156
},
"Accessbility": {
"Accessibility Core Metrics": -0.00108539,
"Cross-Browser Compatibility": 0.00506464,
"Mobile Device Compatibility": -0.0022893
},
"Maintainability": {
"Code Redundancy Rate": 0.00312475,
"Comment Rate": 0.00297972
},
"Alignment": {
"Functional Alignment": 0.01578654,
"Visual Alignment": 0.0083721,
"Content Alignment": 0.00460275
},
"Overall Score": {
"Overall Score": 0.11756437
}
},
{
"ID": 6,
"Model": "Qwen3-Coder-Plus",
"Code Quality": {
"General Functionality Correctness": -0.0128155,
"Best Practices": -0.00161271,
"Error Handling": 0.0035606,
"Runtime Console Errors": 0.0032964,
"Static Syntax Checking (Linting)": 0.00125652
},
"Visual Quality": {
"General Visual Experience": -0.01612824,
"Component Style Consistency": 0.00200508,
"Icon Style Consistency": -0.00595689,
"Layout Consistency": 0.00109076,
"Layout Sparsity": 0.00200298,
"Visual Harmony Degree": 0.00055924
},
"Content Quality": {
"Copywriting Quality": 2.584e-05,
"Media Quality": -0.01057882,
"Placeholder Quality": -0.00113752,
"Resource Validity": 0.0073784
},
"Performance Quality": {
"General Performance": 0.01699388
},
"Accessbility": {
"Accessibility Core Metrics": 0.00585971,
"Cross-Browser Compatibility": -0.00038794,
"Mobile Device Compatibility": 0.0034437
},
"Maintainability": {
"Code Redundancy Rate": 0.00833554,
"Comment Rate": 0.00671238
},
"Alignment": {
"Functional Alignment": -0.01554735,
"Visual Alignment": -0.0104533,
"Content Alignment": -0.01097775
},
"Overall Score": {
"Overall Score": -0.02307499
}
},
{
"ID": 7,
"Model": "Qwen3-235B-A22B-Instruct",
"Code Quality": {
"General Functionality Correctness": -0.00955567,
"Best Practices": -0.00576477,
"Error Handling": 0.0029659,
"Runtime Console Errors": -0.0010004,
"Static Syntax Checking (Linting)": -0.00041588
},
"Visual Quality": {
"General Visual Experience": 0.00660092,
"Component Style Consistency": 0.0018081,
"Icon Style Consistency": -0.00373551,
"Layout Consistency": 0.0021164,
"Layout Sparsity": -0.0016872,
"Visual Harmony Degree": -0.00191208
},
"Content Quality": {
"Copywriting Quality": 0.00166991,
"Media Quality": -0.00163058,
"Placeholder Quality": -0.00082904,
"Resource Validity": -0.005244
},
"Performance Quality": {
"General Performance": 0.00682261
},
"Accessbility": {
"Accessibility Core Metrics": 2.094e-05,
"Cross-Browser Compatibility": -0.00320586,
"Mobile Device Compatibility": 0.0053703
},
"Maintainability": {
"Code Redundancy Rate": 0.00558145,
"Comment Rate": -0.00026166
},
"Alignment": {
"Functional Alignment": -0.00052059,
"Visual Alignment": -5.676e-05,
"Content Alignment": 0.002499
},
"Overall Score": {
"Overall Score": -0.00036447
}
},
{
"ID": 8,
"Model": "MiniMax-M2",
"Code Quality": {
"General Functionality Correctness": 0.0211546,
"Best Practices": 0.00237303,
"Error Handling": -0.0082897,
"Runtime Console Errors": 0.00029315,
"Static Syntax Checking (Linting)": -0.00421208
},
"Visual Quality": {
"General Visual Experience": -0.00756852,
"Component Style Consistency": -0.00367941,
"Icon Style Consistency": 0.00108609,
"Layout Consistency": 0.00043512,
"Layout Sparsity": -0.00101916,
"Visual Harmony Degree": 0.00130448
},
"Content Quality": {
"Copywriting Quality": 0.00075582,
"Media Quality": -0.01503166,
"Placeholder Quality": 0.00384395,
"Resource Validity": 0.00479872
},
"Performance Quality": {
"General Performance": 0.00404345
},
"Accessbility": {
"Accessibility Core Metrics": -0.00969871,
"Cross-Browser Compatibility": 0.00376992,
"Mobile Device Compatibility": -0.0046956
},
"Maintainability": {
"Code Redundancy Rate": -0.00308165,
"Comment Rate": 0.02576016
},
"Alignment": {
"Functional Alignment": 0.03196704,
"Visual Alignment": 0.01498464,
"Content Alignment": 0.01964775
},
"Overall Score": {
"Overall Score": 0.07894143
}
},
{
"ID": 9,
"Model": "Gemini-2.5-Pro",
"Code Quality": {
"General Functionality Correctness": 0.01278301,
"Best Practices": -0.00449064,
"Error Handling": 0.0015656,
"Runtime Console Errors": -0.00031775,
"Static Syntax Checking (Linting)": -0.0006586
},
"Visual Quality": {
"General Visual Experience": 0.01057044,
"Component Style Consistency": -0.00130536,
"Icon Style Consistency": 0.00690768,
"Layout Consistency": -0.00165464,
"Layout Sparsity": -0.0024738,
"Visual Harmony Degree": -0.00214396
},
"Content Quality": {
"Copywriting Quality": 0.00197676,
"Media Quality": -0.00679896,
"Placeholder Quality": 0.00311854,
"Resource Validity": -0.00089792
},
"Performance Quality": {
"General Performance": -0.02252942
},
"Accessbility": {
"Accessibility Core Metrics": 0.00232783,
"Cross-Browser Compatibility": 0.00342958,
"Mobile Device Compatibility": -0.0024687
},
"Maintainability": {
"Code Redundancy Rate": -0.00605124,
"Comment Rate": -0.01134216
},
"Alignment": {
"Functional Alignment": 0.00907515,
"Visual Alignment": 0.01018842,
"Content Alignment": 0.0038505
},
"Overall Score": {
"Overall Score": 0.00266036
}
},
{
"ID": 10,
"Model": "GPT-4o-2024-11-20",
"Code Quality": {
"General Functionality Correctness": -0.02331699,
"Best Practices": 0.00252153,
"Error Handling": 0.0073473,
"Runtime Console Errors": -0.0081959,
"Static Syntax Checking (Linting)": 0.00164576
},
"Visual Quality": {
"General Visual Experience": -0.00533596,
"Component Style Consistency": 0.00363825,
"Icon Style Consistency": -0.00595689,
"Layout Consistency": 0.001998,
"Layout Sparsity": -0.00717288,
"Visual Harmony Degree": -0.00406348
},
"Content Quality": {
"Copywriting Quality": 0.00333013,
"Media Quality": -0.00673246,
"Placeholder Quality": 0.00324627,
"Resource Validity": -0.01890416
},
"Performance Quality": {
"General Performance": -0.02486437
},
"Accessbility": {
"Accessibility Core Metrics": 0.00831667,
"Cross-Browser Compatibility": -0.017255,
"Mobile Device Compatibility": 0.0048594
},
"Maintainability": {
"Code Redundancy Rate": -0.0020257,
"Comment Rate": -0.0516912
},
"Alignment": {
"Functional Alignment": -0.11046357,
"Visual Alignment": -0.06624838,
"Content Alignment": -0.071247
},
"Overall Score": {
"Overall Score": -0.3865
}
},
{
"ID": 11,
"Model": "GPT-5-Codex-High",
"Code Quality": {
"General Functionality Correctness": 0.02510394,
"Best Practices": -0.02013363,
"Error Handling": -0.0028557,
"Runtime Console Errors": 0.0028864,
"Static Syntax Checking (Linting)": -0.00099308
},
"Visual Quality": {
"General Visual Experience": 0.0237888,
"Component Style Consistency": 1.176e-05,
"Icon Style Consistency": 0.00155472,
"Layout Consistency": -0.00385244,
"Layout Sparsity": 0.00267444,
"Visual Harmony Degree": -0.00120404
},
"Content Quality": {
"Copywriting Quality": -0.00319124,
"Media Quality": -0.00688142,
"Placeholder Quality": 0.00379093,
"Resource Validity": -0.00515568
},
"Performance Quality": {
"General Performance": -0.02136764
},
"Accessbility": {
"Accessibility Core Metrics": 0.00782109,
"Cross-Browser Compatibility": 0.002261,
"Mobile Device Compatibility": 0.0076947
},
"Maintainability": {
"Code Redundancy Rate": -0.00535733,
"Comment Rate": -0.0698739
},
"Alignment": {
"Functional Alignment": 0.02103465,
"Visual Alignment": 0.01796454,
"Content Alignment": 0.0238935
},
"Overall Score": {
"Overall Score": -0.0003
}
},
{
"ID": 12,
"Model": "GPT-5-High",
"Code Quality": {
"General Functionality Correctness": 0.03342499,
"Best Practices": 0.00324621,
"Error Handling": -0.012787,
"Runtime Console Errors": 0.00201105,
"Static Syntax Checking (Linting)": -0.00440596
},
"Visual Quality": {
"General Visual Experience": 0.02114324,
"Component Style Consistency": -0.00308259,
"Icon Style Consistency": -0.00250182,
"Layout Consistency": -0.00359936,
"Layout Sparsity": 0.00063156,
"Visual Harmony Degree": 0.0009796
},
"Content Quality": {
"Copywriting Quality": -0.00213826,
"Media Quality": -0.01566474,
"Placeholder Quality": 0.00407772,
"Resource Validity": 0.0020056
},
"Performance Quality": {
"General Performance": 0.01268846
},
"Accessbility": {
"Accessibility Core Metrics": -0.01463008,
"Cross-Browser Compatibility": 0.00531692,
"Mobile Device Compatibility": -0.0111384
},
"Maintainability": {
"Code Redundancy Rate": -0.01040865,
"Comment Rate": 0.0192507
},
"Alignment": {
"Functional Alignment": 0.05508405,
"Visual Alignment": 0.02362162,
"Content Alignment": 0.03499875
},
"Overall Score": {
"Overall Score": 0.13812361
}
},
{
"ID": 13,
"Model": "Manus",
"Code Quality": {
"General Functionality Correctness": 0.00822358,
"Best Practices": -0.00065637,
"Error Handling": -0.0035435,
"Runtime Console Errors": -0.0051086,
"Static Syntax Checking (Linting)": 0.00356532
},
"Visual Quality": {
"General Visual Experience": -0.01029904,
"Component Style Consistency": 0.00369117,
"Icon Style Consistency": -0.00177243,
"Layout Consistency": 0.00010064,
"Layout Sparsity": 0.00083562,
"Visual Harmony Degree": -0.00017856
},
"Content Quality": {
"Copywriting Quality": -0.00071706,
"Media Quality": -0.0020482,
"Placeholder Quality": 0.00181232,
"Resource Validity": 0.00945024
},
"Performance Quality": {
"General Performance": -0.0055811
},
"Accessbility": {
"Accessibility Core Metrics": -0.0010819,
"Cross-Browser Compatibility": -0.0102935,
"Mobile Device Compatibility": 0.0013728
},
"Maintainability": {
"Code Redundancy Rate": -0.01002506,
"Comment Rate": 0.02587764
},
"Alignment": {
"Functional Alignment": 0.03295194,
"Visual Alignment": 0.00329208,
"Content Alignment": 0.01255875
},
"Overall Score": {
"Overall Score": 0.05242678
}
},
{
"ID": 14,
"Model": "MiniMax Agent",
"Code Quality": {
"General Functionality Correctness": -0.00287356,
"Best Practices": 0.00569349,
"Error Handling": -0.0056962,
"Runtime Console Errors": -0.0028126,
"Static Syntax Checking (Linting)": 0.00356532
},
"Visual Quality": {
"General Visual Experience": -0.01220356,
"Component Style Consistency": -0.00678993,
"Icon Style Consistency": -0.00524349,
"Layout Consistency": 0.0002886,
"Layout Sparsity": -0.00028272,
"Visual Harmony Degree": -0.00020584
},
"Content Quality": {
"Copywriting Quality": -0.00345287,
"Media Quality": 0.03579296,
"Placeholder Quality": 0.00577918,
"Resource Validity": 0.0245824
},
"Performance Quality": {
"General Performance": -0.01386163
},
"Accessbility": {
"Accessibility Core Metrics": -0.00083411,
"Cross-Browser Compatibility": -0.01517726,
"Mobile Device Compatibility": 0.0029679
},
"Maintainability": {
"Code Redundancy Rate": -0.02048112,
"Comment Rate": 0.03050208
},
"Alignment": {
"Functional Alignment": 0.01709505,
"Visual Alignment": 0.00768152,
"Content Alignment": 0.000255
},
"Overall Score": {
"Overall Score": 0.04428861
}
}
]