CoolFace
Apppublic

CompileError/WebCoderBench

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes
weighted_z_score.json633 linesDownload Raw Back to src
1[2    {3        "ID": 1,4        "Model": "DeepSeek-R1-0528",5        "Code Quality": {6            "General Functionality Correctness": -0.01335339,7            "Best Practices": 0.00373032,8            "Error Handling": 0.0030818,9            "Runtime Console Errors": 0.0019229,10            "Static Syntax Checking (Linting)": 0.0015406811        },12        "Visual Quality": {13            "General Visual Experience": -0.00933616,14            "Component Style Consistency": -0.0006909,15            "Icon Style Consistency": -0.00721026,16            "Layout Consistency": -0.00078884,17            "Layout Sparsity": 0.00297996,18            "Visual Harmony Degree": 0.0024204819        },20        "Content Quality": {21            "Copywriting Quality": -0.00165376,22            "Media Quality": 0.00281694,23            "Placeholder Quality": 0.00030848,24            "Resource Validity": 0.0165894425        },26        "Performance Quality": {27            "General Performance": 0.0028247228        },29        "Accessbility": {30            "Accessibility Core Metrics": 0.00500117,31            "Cross-Browser Compatibility": 0.0041055,32            "Mobile Device Compatibility": 0.004196433        },34        "Maintainability": {35            "Code Redundancy Rate": 0.00181882,36            "Comment Rate": 0.0090833437        },38        "Alignment": {39            "Functional Alignment": -0.00980679,40            "Visual Alignment": 0.00207174,41            "Content Alignment": 0.0024862542        },43        "Overall Score": {44            "Overall Score": 0.0241388445        }46    },47    {48        "ID": 2,49        "Model": "DeepSeek-V3.1",50        "Code Quality": {51            "General Functionality Correctness": -0.01524503,52            "Best Practices": 0.00343926,53            "Error Handling": 0.0028842,54            "Runtime Console Errors": -0.0005822,55            "Static Syntax Checking (Linting)": 0.0008909656        },57        "Visual Quality": {58            "General Visual Experience": -0.02084588,59            "Component Style Consistency": 0.00117747,60            "Icon Style Consistency": 0.00321276,61            "Layout Consistency": 0.0007474,62            "Layout Sparsity": -0.00083334,63            "Visual Harmony Degree": 0.0005294864        },65        "Content Quality": {66            "Copywriting Quality": -0.00031331,67            "Media Quality": -0.00173964,68            "Placeholder Quality": -0.00449224,69            "Resource Validity": -0.0038897670        },71        "Performance Quality": {72            "General Performance": 0.0081780273        },74        "Accessbility": {75            "Accessibility Core Metrics": -0.00281294,76            "Cross-Browser Compatibility": -0.00501704,77            "Mobile Device Compatibility": -0.003923478        },79        "Maintainability": {80            "Code Redundancy Rate": 0.00255583,81            "Comment Rate": -0.0029530282        },83        "Alignment": {84            "Functional Alignment": -1.407e-05,85            "Visual Alignment": 0.00348128,86            "Content Alignment": -0.00321387        },88        "Overall Score": {89            "Overall Score": -0.0387782190        }91    },92    {93        "ID": 3,94        "Model": "DeepSeek-V3.1-Terminus",95        "Code Quality": {96            "General Functionality Correctness": -0.01027406,97            "Best Practices": 0.00585387,98            "Error Handling": 0.0015029,99            "Runtime Console Errors": 0.00306475,100            "Static Syntax Checking (Linting)": 0.0015688101        },102        "Visual Quality": {103            "General Visual Experience": 0.01755368,104            "Component Style Consistency": 0.00096285,105            "Icon Style Consistency": -0.00284745,106            "Layout Consistency": 0.000518,107            "Layout Sparsity": 0.00273486,108            "Visual Harmony Degree": 0.00213404109        },110        "Content Quality": {111            "Copywriting Quality": -0.00098515,112            "Media Quality": -0.01508486,113            "Placeholder Quality": -0.0035427,114            "Resource Validity": 0.00384192115        },116        "Performance Quality": {117            "General Performance": 0.01370217118        },119        "Accessbility": {120            "Accessibility Core Metrics": 0.00354933,121            "Cross-Browser Compatibility": 0.003689,122            "Mobile Device Compatibility": 0.003627123        },124        "Maintainability": {125            "Code Redundancy Rate": 0.00548663,126            "Comment Rate": 0.02034006127        },128        "Alignment": {129            "Functional Alignment": 0.00519183,130            "Visual Alignment": -0.00027434,131            "Content Alignment": 0.000306132        },133        "Overall Score": {134            "Overall Score": 0.06261913135        }136    },137    {138        "ID": 4,139        "Model": "DeepSeek-V3.1-Thinking",140        "Code Quality": {141            "General Functionality Correctness": -0.01457718,142            "Best Practices": 0.00313038,143            "Error Handling": 0.0030058,144            "Runtime Console Errors": -0.0019434,145            "Static Syntax Checking (Linting)": 0.0005698146        },147        "Visual Quality": {148            "General Visual Experience": -0.02045648,149            "Component Style Consistency": 0.00071736,150            "Icon Style Consistency": 0.00356823,151            "Layout Consistency": 0.00115588,152            "Layout Sparsity": -0.00069084,153            "Visual Harmony Degree": 0.0006076154        },155        "Content Quality": {156            "Copywriting Quality": -0.00042959,157            "Media Quality": 0.0033516,158            "Placeholder Quality": -0.00468022,159            "Resource Validity": -0.00267904160        },161        "Performance Quality": {162            "General Performance": 0.01169753163        },164        "Accessbility": {165            "Accessibility Core Metrics": -0.00292462,166            "Cross-Browser Compatibility": -0.00256564,167            "Mobile Device Compatibility": -0.0049686168        },169        "Maintainability": {170            "Code Redundancy Rate": 0.0032756,171            "Comment Rate": -0.0036312172        },173        "Alignment": {174            "Functional Alignment": -0.00137886,175            "Visual Alignment": -0.00238392,176            "Content Alignment": -0.00503625177        },178        "Overall Score": {179            "Overall Score": -0.03726606180        }181    },182    {183        "ID": 5,184        "Model": "GLM-4.5",185        "Code Quality": {186            "General Functionality Correctness": -0.0075088,187            "Best Practices": 0.00487674,188            "Error Handling": -0.0003439,189            "Runtime Console Errors": 0.0041369,190            "Static Syntax Checking (Linting)": 0.0015984191        },192        "Visual Quality": {193            "General Visual Experience": 0.018408,194            "Component Style Consistency": 0.00127008,195            "Icon Style Consistency": 0.00048216,196            "Layout Consistency": 0.00048396,197            "Layout Sparsity": 0.00171342,198            "Visual Harmony Degree": 0.0009672199        },200        "Content Quality": {201            "Copywriting Quality": -0.00089148,202            "Media Quality": 0.02315264,203            "Placeholder Quality": 0.00584184,204            "Resource Validity": 0.02221984205        },206        "Performance Quality": {207            "General Performance": 0.00460156208        },209        "Accessbility": {210            "Accessibility Core Metrics": -0.00108539,211            "Cross-Browser Compatibility": 0.00506464,212            "Mobile Device Compatibility": -0.0022893213        },214        "Maintainability": {215            "Code Redundancy Rate": 0.00312475,216            "Comment Rate": 0.00297972217        },218        "Alignment": {219            "Functional Alignment": 0.01578654,220            "Visual Alignment": 0.0083721,221            "Content Alignment": 0.00460275222        },223        "Overall Score": {224            "Overall Score": 0.11756437225        }226    },227    {228        "ID": 6,229        "Model": "Qwen3-Coder-Plus",230        "Code Quality": {231            "General Functionality Correctness": -0.0128155,232            "Best Practices": -0.00161271,233            "Error Handling": 0.0035606,234            "Runtime Console Errors": 0.0032964,235            "Static Syntax Checking (Linting)": 0.00125652236        },237        "Visual Quality": {238            "General Visual Experience": -0.01612824,239            "Component Style Consistency": 0.00200508,240            "Icon Style Consistency": -0.00595689,241            "Layout Consistency": 0.00109076,242            "Layout Sparsity": 0.00200298,243            "Visual Harmony Degree": 0.00055924244        },245        "Content Quality": {246            "Copywriting Quality": 2.584e-05,247            "Media Quality": -0.01057882,248            "Placeholder Quality": -0.00113752,249            "Resource Validity": 0.0073784250        },251        "Performance Quality": {252            "General Performance": 0.01699388253        },254        "Accessbility": {255            "Accessibility Core Metrics": 0.00585971,256            "Cross-Browser Compatibility": -0.00038794,257            "Mobile Device Compatibility": 0.0034437258        },259        "Maintainability": {260            "Code Redundancy Rate": 0.00833554,261            "Comment Rate": 0.00671238262        },263        "Alignment": {264            "Functional Alignment": -0.01554735,265            "Visual Alignment": -0.0104533,266            "Content Alignment": -0.01097775267        },268        "Overall Score": {269            "Overall Score": -0.02307499270        }271    },272    {273        "ID": 7,274        "Model": "Qwen3-235B-A22B-Instruct",275        "Code Quality": {276            "General Functionality Correctness": -0.00955567,277            "Best Practices": -0.00576477,278            "Error Handling": 0.0029659,279            "Runtime Console Errors": -0.0010004,280            "Static Syntax Checking (Linting)": -0.00041588281        },282        "Visual Quality": {283            "General Visual Experience": 0.00660092,284            "Component Style Consistency": 0.0018081,285            "Icon Style Consistency": -0.00373551,286            "Layout Consistency": 0.0021164,287            "Layout Sparsity": -0.0016872,288            "Visual Harmony Degree": -0.00191208289        },290        "Content Quality": {291            "Copywriting Quality": 0.00166991,292            "Media Quality": -0.00163058,293            "Placeholder Quality": -0.00082904,294            "Resource Validity": -0.005244295        },296        "Performance Quality": {297            "General Performance": 0.00682261298        },299        "Accessbility": {300            "Accessibility Core Metrics": 2.094e-05,301            "Cross-Browser Compatibility": -0.00320586,302            "Mobile Device Compatibility": 0.0053703303        },304        "Maintainability": {305            "Code Redundancy Rate": 0.00558145,306            "Comment Rate": -0.00026166307        },308        "Alignment": {309            "Functional Alignment": -0.00052059,310            "Visual Alignment": -5.676e-05,311            "Content Alignment": 0.002499312        },313        "Overall Score": {314            "Overall Score": -0.00036447315        }316    },317    {318        "ID": 8,319        "Model": "MiniMax-M2",320        "Code Quality": {321            "General Functionality Correctness": 0.0211546,322            "Best Practices": 0.00237303,323            "Error Handling": -0.0082897,324            "Runtime Console Errors": 0.00029315,325            "Static Syntax Checking (Linting)": -0.00421208326        },327        "Visual Quality": {328            "General Visual Experience": -0.00756852,329            "Component Style Consistency": -0.00367941,330            "Icon Style Consistency": 0.00108609,331            "Layout Consistency": 0.00043512,332            "Layout Sparsity": -0.00101916,333            "Visual Harmony Degree": 0.00130448334        },335        "Content Quality": {336            "Copywriting Quality": 0.00075582,337            "Media Quality": -0.01503166,338            "Placeholder Quality": 0.00384395,339            "Resource Validity": 0.00479872340        },341        "Performance Quality": {342            "General Performance": 0.00404345343        },344        "Accessbility": {345            "Accessibility Core Metrics": -0.00969871,346            "Cross-Browser Compatibility": 0.00376992,347            "Mobile Device Compatibility": -0.0046956348        },349        "Maintainability": {350            "Code Redundancy Rate": -0.00308165,351            "Comment Rate": 0.02576016352        },353        "Alignment": {354            "Functional Alignment": 0.03196704,355            "Visual Alignment": 0.01498464,356            "Content Alignment": 0.01964775357        },358        "Overall Score": {359            "Overall Score": 0.07894143360        }361    },362    {363        "ID": 9,364        "Model": "Gemini-2.5-Pro",365        "Code Quality": {366            "General Functionality Correctness": 0.01278301,367            "Best Practices": -0.00449064,368            "Error Handling": 0.0015656,369            "Runtime Console Errors": -0.00031775,370            "Static Syntax Checking (Linting)": -0.0006586371        },372        "Visual Quality": {373            "General Visual Experience": 0.01057044,374            "Component Style Consistency": -0.00130536,375            "Icon Style Consistency": 0.00690768,376            "Layout Consistency": -0.00165464,377            "Layout Sparsity": -0.0024738,378            "Visual Harmony Degree": -0.00214396379        },380        "Content Quality": {381            "Copywriting Quality": 0.00197676,382            "Media Quality": -0.00679896,383            "Placeholder Quality": 0.00311854,384            "Resource Validity": -0.00089792385        },386        "Performance Quality": {387            "General Performance": -0.02252942388        },389        "Accessbility": {390            "Accessibility Core Metrics": 0.00232783,391            "Cross-Browser Compatibility": 0.00342958,392            "Mobile Device Compatibility": -0.0024687393        },394        "Maintainability": {395            "Code Redundancy Rate": -0.00605124,396            "Comment Rate": -0.01134216397        },398        "Alignment": {399            "Functional Alignment": 0.00907515,400            "Visual Alignment": 0.01018842,401            "Content Alignment": 0.0038505402        },403        "Overall Score": {404            "Overall Score": 0.00266036405        }406    },407    {408        "ID": 10,409        "Model": "GPT-4o-2024-11-20",410        "Code Quality": {411            "General Functionality Correctness": -0.02331699,412            "Best Practices": 0.00252153,413            "Error Handling": 0.0073473,414            "Runtime Console Errors": -0.0081959,415            "Static Syntax Checking (Linting)": 0.00164576416        },417        "Visual Quality": {418            "General Visual Experience": -0.00533596,419            "Component Style Consistency": 0.00363825,420            "Icon Style Consistency": -0.00595689,421            "Layout Consistency": 0.001998,422            "Layout Sparsity": -0.00717288,423            "Visual Harmony Degree": -0.00406348424        },425        "Content Quality": {426            "Copywriting Quality": 0.00333013,427            "Media Quality": -0.00673246,428            "Placeholder Quality": 0.00324627,429            "Resource Validity": -0.01890416430        },431        "Performance Quality": {432            "General Performance": -0.02486437433        },434        "Accessbility": {435            "Accessibility Core Metrics": 0.00831667,436            "Cross-Browser Compatibility": -0.017255,437            "Mobile Device Compatibility": 0.0048594438        },439        "Maintainability": {440            "Code Redundancy Rate": -0.0020257,441            "Comment Rate": -0.0516912442        },443        "Alignment": {444            "Functional Alignment": -0.11046357,445            "Visual Alignment": -0.06624838,446            "Content Alignment": -0.071247447        },448        "Overall Score": {449            "Overall Score": -0.3865450        }451    },452    {453        "ID": 11,454        "Model": "GPT-5-Codex-High",455        "Code Quality": {456            "General Functionality Correctness": 0.02510394,457            "Best Practices": -0.02013363,458            "Error Handling": -0.0028557,459            "Runtime Console Errors": 0.0028864,460            "Static Syntax Checking (Linting)": -0.00099308461        },462        "Visual Quality": {463            "General Visual Experience": 0.0237888,464            "Component Style Consistency": 1.176e-05,465            "Icon Style Consistency": 0.00155472,466            "Layout Consistency": -0.00385244,467            "Layout Sparsity": 0.00267444,468            "Visual Harmony Degree": -0.00120404469        },470        "Content Quality": {471            "Copywriting Quality": -0.00319124,472            "Media Quality": -0.00688142,473            "Placeholder Quality": 0.00379093,474            "Resource Validity": -0.00515568475        },476        "Performance Quality": {477            "General Performance": -0.02136764478        },479        "Accessbility": {480            "Accessibility Core Metrics": 0.00782109,481            "Cross-Browser Compatibility": 0.002261,482            "Mobile Device Compatibility": 0.0076947483        },484        "Maintainability": {485            "Code Redundancy Rate": -0.00535733,486            "Comment Rate": -0.0698739487        },488        "Alignment": {489            "Functional Alignment": 0.02103465,490            "Visual Alignment": 0.01796454,491            "Content Alignment": 0.0238935492        },493        "Overall Score": {494            "Overall Score": -0.0003495        }496    },497    {498        "ID": 12,499        "Model": "GPT-5-High",500        "Code Quality": {501            "General Functionality Correctness": 0.03342499,502            "Best Practices": 0.00324621,503            "Error Handling": -0.012787,504            "Runtime Console Errors": 0.00201105,505            "Static Syntax Checking (Linting)": -0.00440596506        },507        "Visual Quality": {508            "General Visual Experience": 0.02114324,509            "Component Style Consistency": -0.00308259,510            "Icon Style Consistency": -0.00250182,511            "Layout Consistency": -0.00359936,512            "Layout Sparsity": 0.00063156,513            "Visual Harmony Degree": 0.0009796514        },515        "Content Quality": {516            "Copywriting Quality": -0.00213826,517            "Media Quality": -0.01566474,518            "Placeholder Quality": 0.00407772,519            "Resource Validity": 0.0020056520        },521        "Performance Quality": {522            "General Performance": 0.01268846523        },524        "Accessbility": {525            "Accessibility Core Metrics": -0.01463008,526            "Cross-Browser Compatibility": 0.00531692,527            "Mobile Device Compatibility": -0.0111384528        },529        "Maintainability": {530            "Code Redundancy Rate": -0.01040865,531            "Comment Rate": 0.0192507532        },533        "Alignment": {534            "Functional Alignment": 0.05508405,535            "Visual Alignment": 0.02362162,536            "Content Alignment": 0.03499875537        },538        "Overall Score": {539            "Overall Score": 0.13812361540        }541    },542    {543        "ID": 13,544        "Model": "Manus",545        "Code Quality": {546            "General Functionality Correctness": 0.00822358,547            "Best Practices": -0.00065637,548            "Error Handling": -0.0035435,549            "Runtime Console Errors": -0.0051086,550            "Static Syntax Checking (Linting)": 0.00356532551        },552        "Visual Quality": {553            "General Visual Experience": -0.01029904,554            "Component Style Consistency": 0.00369117,555            "Icon Style Consistency": -0.00177243,556            "Layout Consistency": 0.00010064,557            "Layout Sparsity": 0.00083562,558            "Visual Harmony Degree": -0.00017856559        },560        "Content Quality": {561            "Copywriting Quality": -0.00071706,562            "Media Quality": -0.0020482,563            "Placeholder Quality": 0.00181232,564            "Resource Validity": 0.00945024565        },566        "Performance Quality": {567            "General Performance": -0.0055811568        },569        "Accessbility": {570            "Accessibility Core Metrics": -0.0010819,571            "Cross-Browser Compatibility": -0.0102935,572            "Mobile Device Compatibility": 0.0013728573        },574        "Maintainability": {575            "Code Redundancy Rate": -0.01002506,576            "Comment Rate": 0.02587764577        },578        "Alignment": {579            "Functional Alignment": 0.03295194,580            "Visual Alignment": 0.00329208,581            "Content Alignment": 0.01255875582        },583        "Overall Score": {584            "Overall Score": 0.05242678585        }586    },587    {588        "ID": 14,589        "Model": "MiniMax Agent",590        "Code Quality": {591            "General Functionality Correctness": -0.00287356,592            "Best Practices": 0.00569349,593            "Error Handling": -0.0056962,594            "Runtime Console Errors": -0.0028126,595            "Static Syntax Checking (Linting)": 0.00356532596        },597        "Visual Quality": {598            "General Visual Experience": -0.01220356,599            "Component Style Consistency": -0.00678993,600            "Icon Style Consistency": -0.00524349,601            "Layout Consistency": 0.0002886,602            "Layout Sparsity": -0.00028272,603            "Visual Harmony Degree": -0.00020584604        },605        "Content Quality": {606            "Copywriting Quality": -0.00345287,607            "Media Quality": 0.03579296,608            "Placeholder Quality": 0.00577918,609            "Resource Validity": 0.0245824610        },611        "Performance Quality": {612            "General Performance": -0.01386163613        },614        "Accessbility": {615            "Accessibility Core Metrics": -0.00083411,616            "Cross-Browser Compatibility": -0.01517726,617            "Mobile Device Compatibility": 0.0029679618        },619        "Maintainability": {620            "Code Redundancy Rate": -0.02048112,621            "Comment Rate": 0.03050208622        },623        "Alignment": {624            "Functional Alignment": 0.01709505,625            "Visual Alignment": 0.00768152,626            "Content Alignment": 0.000255627        },628        "Overall Score": {629            "Overall Score": 0.04428861630        }631    }632]633