CoolFace
Apppublic

CompileError/WebCoderBench

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes
unweighted_z_score.json591 linesDownload Raw Back to src
1[2    {3        "ID": 1,4        "Model": "DeepSeek-R1-0528",5        "Code Quality": {6            "General Functionality Correctness": -0.3699,7            "Best Practices": 0.1256,8            "Error Handling": 0.1622,9            "Runtime Console Errors": 0.0938,10            "Static Syntax Checking (Linting)": 0.104111        },12        "Visual Quality": {13            "General Visual Experience": -0.3956,14            "Component Style Consistency": -0.047,15            "Icon Style Consistency": -0.5862,16            "Layout Consistency": -0.0533,17            "Layout Sparsity": 0.2614,18            "Visual Harmony Degree": 0.195219        },20        "Content Quality": {21            "Copywriting Quality": -0.0512,22            "Media Quality": 0.1059,23            "Placeholder Quality": 0.0128,24            "Resource Validity": 0.450825        },26        "Performance Quality": {27            "General Performance": 0.024828        },29        "Accessbility": {30            "Accessibility Core Metrics": 0.1433,31            "Cross-Browser Compatibility": 0.1725,32            "Mobile Device Compatibility": 0.107633        },34        "Maintainability": {35            "Code Redundancy Rate": 0.0422,36            "Comment Rate": 0.170137        },38        "Alignment": {39            "Functional Alignment": -0.0697,40            "Visual Alignment": 0.0219,41            "Content Alignment": 0.019542        }43    },44    {45        "ID": 2,46        "Model": "DeepSeek-V3.1",47        "Code Quality": {48            "General Functionality Correctness": -0.4223,49            "Best Practices": 0.1158,50            "Error Handling": 0.1518,51            "Runtime Console Errors": -0.0284,52            "Static Syntax Checking (Linting)": 0.060253        },54        "Visual Quality": {55            "General Visual Experience": -0.8833,56            "Component Style Consistency": 0.0801,57            "Icon Style Consistency": 0.2612,58            "Layout Consistency": 0.0505,59            "Layout Sparsity": -0.0731,60            "Visual Harmony Degree": 0.042761        },62        "Content Quality": {63            "Copywriting Quality": -0.0097,64            "Media Quality": -0.0654,65            "Placeholder Quality": -0.1864,66            "Resource Validity": -0.105767        },68        "Performance Quality": {69            "General Performance": 0.071870        },71        "Accessbility": {72            "Accessibility Core Metrics": -0.0806,73            "Cross-Browser Compatibility": -0.2108,74            "Mobile Device Compatibility": -0.100675        },76        "Maintainability": {77            "Code Redundancy Rate": 0.0593,78            "Comment Rate": -0.055379        },80        "Alignment": {81            "Functional Alignment": -0.0001,82            "Visual Alignment": 0.0368,83            "Content Alignment": -0.025284        }85    },86    {87        "ID": 3,88        "Model": "DeepSeek-V3.1-Terminus",89        "Code Quality": {90            "General Functionality Correctness": -0.2846,91            "Best Practices": 0.1971,92            "Error Handling": 0.0791,93            "Runtime Console Errors": 0.1495,94            "Static Syntax Checking (Linting)": 0.10695        },96        "Visual Quality": {97            "General Visual Experience": 0.7438,98            "Component Style Consistency": 0.0655,99            "Icon Style Consistency": -0.2315,100            "Layout Consistency": 0.035,101            "Layout Sparsity": 0.2399,102            "Visual Harmony Degree": 0.1721103        },104        "Content Quality": {105            "Copywriting Quality": -0.0305,106            "Media Quality": -0.5671,107            "Placeholder Quality": -0.147,108            "Resource Validity": 0.1044109        },110        "Performance Quality": {111            "General Performance": 0.1203112        },113        "Accessbility": {114            "Accessibility Core Metrics": 0.1017,115            "Cross-Browser Compatibility": 0.155,116            "Mobile Device Compatibility": 0.093117        },118        "Maintainability": {119            "Code Redundancy Rate": 0.1273,120            "Comment Rate": 0.3809121        },122        "Alignment": {123            "Functional Alignment": 0.0369,124            "Visual Alignment": -0.0029,125            "Content Alignment": 0.0024126        }127    },128    {129        "ID": 4,130        "Model": "DeepSeek-V3.1-Thinking",131        "Code Quality": {132            "General Functionality Correctness": -0.4038,133            "Best Practices": 0.1054,134            "Error Handling": 0.1582,135            "Runtime Console Errors": -0.0948,136            "Static Syntax Checking (Linting)": 0.0385137        },138        "Visual Quality": {139            "General Visual Experience": -0.8668,140            "Component Style Consistency": 0.0488,141            "Icon Style Consistency": 0.2901,142            "Layout Consistency": 0.0781,143            "Layout Sparsity": -0.0606,144            "Visual Harmony Degree": 0.049145        },146        "Content Quality": {147            "Copywriting Quality": -0.0133,148            "Media Quality": 0.126,149            "Placeholder Quality": -0.1942,150            "Resource Validity": -0.0728151        },152        "Performance Quality": {153            "General Performance": 0.1027154        },155        "Accessbility": {156            "Accessibility Core Metrics": -0.0838,157            "Cross-Browser Compatibility": -0.1078,158            "Mobile Device Compatibility": -0.1274159        },160        "Maintainability": {161            "Code Redundancy Rate": 0.076,162            "Comment Rate": -0.068163        },164        "Alignment": {165            "Functional Alignment": -0.0098,166            "Visual Alignment": -0.0252,167            "Content Alignment": -0.0395168        }169    },170    {171        "ID": 5,172        "Model": "GLM-4.5",173        "Code Quality": {174            "General Functionality Correctness": -0.208,175            "Best Practices": 0.1642,176            "Error Handling": -0.0181,177            "Runtime Console Errors": 0.2018,178            "Static Syntax Checking (Linting)": 0.108179        },180        "Visual Quality": {181            "General Visual Experience": 0.78,182            "Component Style Consistency": 0.0864,183            "Icon Style Consistency": 0.0392,184            "Layout Consistency": 0.0327,185            "Layout Sparsity": 0.1503,186            "Visual Harmony Degree": 0.078187        },188        "Content Quality": {189            "Copywriting Quality": -0.0276,190            "Media Quality": 0.8704,191            "Placeholder Quality": 0.2424,192            "Resource Validity": 0.6038193        },194        "Performance Quality": {195            "General Performance": 0.0404196        },197        "Accessbility": {198            "Accessibility Core Metrics": -0.0311,199            "Cross-Browser Compatibility": 0.2128,200            "Mobile Device Compatibility": -0.0587201        },202        "Maintainability": {203            "Code Redundancy Rate": 0.0725,204            "Comment Rate": 0.0558205        },206        "Alignment": {207            "Functional Alignment": 0.1122,208            "Visual Alignment": 0.0885,209            "Content Alignment": 0.0361210        }211    },212    {213        "ID": 6,214        "Model": "Qwen3-Coder-Plus",215        "Code Quality": {216            "General Functionality Correctness": -0.355,217            "Best Practices": -0.0543,218            "Error Handling": 0.1874,219            "Runtime Console Errors": 0.1608,220            "Static Syntax Checking (Linting)": 0.0849221        },222        "Visual Quality": {223            "General Visual Experience": -0.6834,224            "Component Style Consistency": 0.1364,225            "Icon Style Consistency": -0.4843,226            "Layout Consistency": 0.0737,227            "Layout Sparsity": 0.1757,228            "Visual Harmony Degree": 0.0451229        },230        "Content Quality": {231            "Copywriting Quality": 0.0008,232            "Media Quality": -0.3977,233            "Placeholder Quality": -0.0472,234            "Resource Validity": 0.2005235        },236        "Performance Quality": {237            "General Performance": 0.1492238        },239        "Accessbility": {240            "Accessibility Core Metrics": 0.1679,241            "Cross-Browser Compatibility": -0.0163,242            "Mobile Device Compatibility": 0.0883243        },244        "Maintainability": {245            "Code Redundancy Rate": 0.1934,246            "Comment Rate": 0.1257247        },248        "Alignment": {249            "Functional Alignment": -0.1105,250            "Visual Alignment": -0.1105,251            "Content Alignment": -0.0861252        }253    },254    {255        "ID": 7,256        "Model": "Qwen3-235B-A22B-Instruct",257        "Code Quality": {258            "General Functionality Correctness": -0.2647,259            "Best Practices": -0.1941,260            "Error Handling": 0.1561,261            "Runtime Console Errors": -0.0488,262            "Static Syntax Checking (Linting)": -0.0281263        },264        "Visual Quality": {265            "General Visual Experience": 0.2797,266            "Component Style Consistency": 0.123,267            "Icon Style Consistency": -0.3037,268            "Layout Consistency": 0.143,269            "Layout Sparsity": -0.148,270            "Visual Harmony Degree": -0.1542271        },272        "Content Quality": {273            "Copywriting Quality": 0.0517,274            "Media Quality": -0.0613,275            "Placeholder Quality": -0.0344,276            "Resource Validity": -0.1425277        },278        "Performance Quality": {279            "General Performance": 0.0599280        },281        "Accessbility": {282            "Accessibility Core Metrics": 0.0006,283            "Cross-Browser Compatibility": -0.1347,284            "Mobile Device Compatibility": 0.1377285        },286        "Maintainability": {287            "Code Redundancy Rate": 0.1295,288            "Comment Rate": -0.0049289        },290        "Alignment": {291            "Functional Alignment": -0.0037,292            "Visual Alignment": -0.0006,293            "Content Alignment": 0.0196294        }295    },296    {297        "ID": 8,298        "Model": "MiniMax-M2",299        "Code Quality": {300            "General Functionality Correctness": 0.586,301            "Best Practices": 0.0799,302            "Error Handling": -0.4363,303            "Runtime Console Errors": 0.0143,304            "Static Syntax Checking (Linting)": -0.2846305        },306        "Visual Quality": {307            "General Visual Experience": -0.3207,308            "Component Style Consistency": -0.2503,309            "Icon Style Consistency": 0.0883,310            "Layout Consistency": 0.0294,311            "Layout Sparsity": -0.0894,312            "Visual Harmony Degree": 0.1052313        },314        "Content Quality": {315            "Copywriting Quality": 0.0234,316            "Media Quality": -0.5651,317            "Placeholder Quality": 0.1595,318            "Resource Validity": 0.1304319        },320        "Performance Quality": {321            "General Performance": 0.0355322        },323        "Accessbility": {324            "Accessibility Core Metrics": -0.2779,325            "Cross-Browser Compatibility": 0.1584,326            "Mobile Device Compatibility": -0.1204327        },328        "Maintainability": {329            "Code Redundancy Rate": -0.0715,330            "Comment Rate": 0.4824331        },332        "Alignment": {333            "Functional Alignment": 0.2272,334            "Visual Alignment": 0.1584,335            "Content Alignment": 0.1541336        }337    },338    {339        "ID": 9,340        "Model": "Gemini-2.5-Pro",341        "Code Quality": {342            "General Functionality Correctness": 0.3541,343            "Best Practices": -0.1512,344            "Error Handling": 0.0824,345            "Runtime Console Errors": -0.0155,346            "Static Syntax Checking (Linting)": -0.0445347        },348        "Visual Quality": {349            "General Visual Experience": 0.4479,350            "Component Style Consistency": -0.0888,351            "Icon Style Consistency": 0.5616,352            "Layout Consistency": -0.1118,353            "Layout Sparsity": -0.217,354            "Visual Harmony Degree": -0.1729355        },356        "Content Quality": {357            "Copywriting Quality": 0.0612,358            "Media Quality": -0.2556,359            "Placeholder Quality": 0.1294,360            "Resource Validity": -0.0244361        },362        "Performance Quality": {363            "General Performance": -0.1978364        },365        "Accessbility": {366            "Accessibility Core Metrics": 0.0667,367            "Cross-Browser Compatibility": 0.1441,368            "Mobile Device Compatibility": -0.0633369        },370        "Maintainability": {371            "Code Redundancy Rate": -0.1404,372            "Comment Rate": -0.2124373        },374        "Alignment": {375            "Functional Alignment": 0.0645,376            "Visual Alignment": 0.1077,377            "Content Alignment": 0.0302378        }379    },380    {381        "ID": 10,382        "Model": "GPT-4o-2024-11-20",383        "Code Quality": {384            "General Functionality Correctness": -0.6459,385            "Best Practices": 0.0849,386            "Error Handling": 0.3867,387            "Runtime Console Errors": -0.3998,388            "Static Syntax Checking (Linting)": 0.1112389        },390        "Visual Quality": {391            "General Visual Experience": -0.2261,392            "Component Style Consistency": 0.2475,393            "Icon Style Consistency": -0.4843,394            "Layout Consistency": 0.135,395            "Layout Sparsity": -0.6292,396            "Visual Harmony Degree": -0.3277397        },398        "Content Quality": {399            "Copywriting Quality": 0.1031,400            "Media Quality": -0.2531,401            "Placeholder Quality": 0.1347,402            "Resource Validity": -0.5137403        },404        "Performance Quality": {405            "General Performance": -0.2183406        },407        "Accessbility": {408            "Accessibility Core Metrics": 0.2383,409            "Cross-Browser Compatibility": -0.725,410            "Mobile Device Compatibility": 0.1246411        },412        "Maintainability": {413            "Code Redundancy Rate": -0.047,414            "Comment Rate": -0.968415        },416        "Alignment": {417            "Functional Alignment": -0.7851,418            "Visual Alignment": -0.7003,419            "Content Alignment": -0.5588420        }421    },422    {423        "ID": 11,424        "Model": "GPT-5-Codex-High",425        "Code Quality": {426            "General Functionality Correctness": 0.6954,427            "Best Practices": -0.6779,428            "Error Handling": -0.1503,429            "Runtime Console Errors": 0.1408,430            "Static Syntax Checking (Linting)": -0.0671431        },432        "Visual Quality": {433            "General Visual Experience": 1.008,434            "Component Style Consistency": 0.0008,435            "Icon Style Consistency": 0.1264,436            "Layout Consistency": -0.2603,437            "Layout Sparsity": 0.2346,438            "Visual Harmony Degree": -0.0971439        },440        "Content Quality": {441            "Copywriting Quality": -0.0988,442            "Media Quality": -0.2587,443            "Placeholder Quality": 0.1573,444            "Resource Validity": -0.1401445        },446        "Performance Quality": {447            "General Performance": -0.1876448        },449        "Accessbility": {450            "Accessibility Core Metrics": 0.2241,451            "Cross-Browser Compatibility": 0.095,452            "Mobile Device Compatibility": 0.1973453        },454        "Maintainability": {455            "Code Redundancy Rate": -0.1243,456            "Comment Rate": -1.3085457        },458        "Alignment": {459            "Functional Alignment": 0.1495,460            "Visual Alignment": 0.1899,461            "Content Alignment": 0.1874462        }463    },464    {465        "ID": 12,466        "Model": "GPT-5-High",467        "Code Quality": {468            "General Functionality Correctness": 0.9259,469            "Best Practices": 0.1093,470            "Error Handling": -0.673,471            "Runtime Console Errors": 0.0981,472            "Static Syntax Checking (Linting)": -0.2977473        },474        "Visual Quality": {475            "General Visual Experience": 0.8959,476            "Component Style Consistency": -0.2097,477            "Icon Style Consistency": -0.2034,478            "Layout Consistency": -0.2432,479            "Layout Sparsity": 0.0554,480            "Visual Harmony Degree": 0.079481        },482        "Content Quality": {483            "Copywriting Quality": -0.0662,484            "Media Quality": -0.5889,485            "Placeholder Quality": 0.1692,486            "Resource Validity": 0.0545487        },488        "Performance Quality": {489            "General Performance": 0.1114490        },491        "Accessbility": {492            "Accessibility Core Metrics": -0.4192,493            "Cross-Browser Compatibility": 0.2234,494            "Mobile Device Compatibility": -0.2856495        },496        "Maintainability": {497            "Code Redundancy Rate": -0.2415,498            "Comment Rate": 0.3605499        },500        "Alignment": {501            "Functional Alignment": 0.3915,502            "Visual Alignment": 0.2497,503            "Content Alignment": 0.2745504        }505    },506    {507        "ID": 13,508        "Model": "Manus",509        "Code Quality": {510            "General Functionality Correctness": 0.2278,511            "Best Practices": -0.0221,512            "Error Handling": -0.1865,513            "Runtime Console Errors": -0.2492,514            "Static Syntax Checking (Linting)": 0.2409515        },516        "Visual Quality": {517            "General Visual Experience": -0.4364,518            "Component Style Consistency": 0.2511,519            "Icon Style Consistency": -0.1441,520            "Layout Consistency": 0.0068,521            "Layout Sparsity": 0.0733,522            "Visual Harmony Degree": -0.0144523        },524        "Content Quality": {525            "Copywriting Quality": -0.0222,526            "Media Quality": -0.077,527            "Placeholder Quality": 0.0752,528            "Resource Validity": 0.2568529        },530        "Performance Quality": {531            "General Performance": -0.049532        },533        "Accessbility": {534            "Accessibility Core Metrics": -0.031,535            "Cross-Browser Compatibility": -0.4325,536            "Mobile Device Compatibility": 0.0352537        },538        "Maintainability": {539            "Code Redundancy Rate": -0.2326,540            "Comment Rate": 0.4846541        },542        "Alignment": {543            "Functional Alignment": 0.2342,544            "Visual Alignment": 0.0348,545            "Content Alignment": 0.0985546        }547    },548    {549        "ID": 14,550        "Model": "MiniMax Agent",551        "Code Quality": {552            "General Functionality Correctness": -0.0796,553            "Best Practices": 0.1917,554            "Error Handling": -0.2998,555            "Runtime Console Errors": -0.1372,556            "Static Syntax Checking (Linting)": 0.2409557        },558        "Visual Quality": {559            "General Visual Experience": -0.5171,560            "Component Style Consistency": -0.4619,561            "Icon Style Consistency": -0.4263,562            "Layout Consistency": 0.0195,563            "Layout Sparsity": -0.0248,564            "Visual Harmony Degree": -0.0166565        },566        "Content Quality": {567            "Copywriting Quality": -0.1069,568            "Media Quality": 1.3456,569            "Placeholder Quality": 0.2398,570            "Resource Validity": 0.668571        },572        "Performance Quality": {573            "General Performance": -0.1217574        },575        "Accessbility": {576            "Accessibility Core Metrics": -0.0239,577            "Cross-Browser Compatibility": -0.6377,578            "Mobile Device Compatibility": 0.0761579        },580        "Maintainability": {581            "Code Redundancy Rate": -0.4752,582            "Comment Rate": 0.5712583        },584        "Alignment": {585            "Functional Alignment": 0.1215,586            "Visual Alignment": 0.0812,587            "Content Alignment": 0.002588        }589    }590]591