Deploy Chinese Writing Bench leaderboard with dual judge support

README.md

@@ -0,0 +1,8 @@
+---
+title: Chinese Writing Bench
+emoji: 🔬
+colorFrom: blue
+colorTo: purple
+sdk: static
+pinned: false
+---

data/all-scores.json

@@ -0,0 +1,236 @@
+{
+  "Mistral-3.1-24B-2503": {
+    "comprehension_score": 4.707142857142857,
+    "structure_score": 4.796428571428572,
+    "prose_style_score": 4.2178571428571425,
+    "creativity_score": 3.914285714285714,
+    "depth_score": 3.9035714285714285,
+    "helpfulness_score": 4.242857142857143,
+    "overall_score": 4.203571428571428
+  },
+  "Phi-4-14B": {
+    "comprehension_score": 4.735714285714286,
+    "structure_score": 4.889285714285714,
+    "prose_style_score": 4.460714285714285,
+    "creativity_score": 4.242857142857143,
+    "depth_score": 4.178571428571429,
+    "helpfulness_score": 4.317857142857143,
+    "overall_score": 4.296428571428572
+  },
+  "gpt-4o-mini-2024-07-18": {
+    "comprehension_score": 4.760714285714286,
+    "structure_score": 4.9,
+    "prose_style_score": 4.542857142857143,
+    "creativity_score": 4.289285714285715,
+    "depth_score": 4.082142857142857,
+    "helpfulness_score": 4.35,
+    "overall_score": 4.321428571428571
+  },
+  "gpt-4.1-mini-2025-04-14": {
+    "comprehension_score": 5.042857142857143,
+    "structure_score": 4.935714285714286,
+    "prose_style_score": 4.675,
+    "creativity_score": 4.335714285714285,
+    "depth_score": 4.2,
+    "helpfulness_score": 4.564285714285714,
+    "overall_score": 4.435714285714286
+  },
+  "Qwen3-30B-A3B": {
+    "comprehension_score": 5.146428571428571,
+    "structure_score": 5.289285714285715,
+    "prose_style_score": 4.853571428571429,
+    "creativity_score": 4.714285714285714,
+    "depth_score": 4.5321428571428575,
+    "helpfulness_score": 4.925,
+    "overall_score": 4.814285714285714
+  },
+  "Qwen3-8B": {
+    "comprehension_score": 5.146428571428571,
+    "structure_score": 5.260714285714286,
+    "prose_style_score": 4.910714285714286,
+    "creativity_score": 4.689285714285714,
+    "depth_score": 4.496428571428571,
+    "helpfulness_score": 4.8464285714285715,
+    "overall_score": 4.817857142857143
+  },
+  "gpt-4o-2024-11-20": {
+    "comprehension_score": 5.2785714285714285,
+    "structure_score": 5.3464285714285715,
+    "prose_style_score": 5.207142857142857,
+    "creativity_score": 5.082142857142857,
+    "depth_score": 4.746428571428571,
+    "helpfulness_score": 5.010714285714286,
+    "overall_score": 4.985714285714286
+  },
+  "gemma3-27b": {
+    "comprehension_score": 5.428571428571429,
+    "structure_score": 5.535714285714286,
+    "prose_style_score": 5.0285714285714285,
+    "creativity_score": 5.121428571428571,
+    "depth_score": 4.8464285714285715,
+    "helpfulness_score": 5.2178571428571425,
+    "overall_score": 5.082142857142857
+  },
+  "Qwen3-32B": {
+    "comprehension_score": 5.457142857142857,
+    "structure_score": 5.628571428571429,
+    "prose_style_score": 5.285714285714286,
+    "creativity_score": 5.078571428571428,
+    "depth_score": 4.882142857142857,
+    "helpfulness_score": 5.314285714285714,
+    "overall_score": 5.2214285714285715
+  },
+  "Mistral-3.2-24B-2506": {
+    "comprehension_score": 5.5321428571428575,
+    "structure_score": 5.817857142857143,
+    "prose_style_score": 5.5321428571428575,
+    "creativity_score": 5.607142857142857,
+    "depth_score": 5.010714285714286,
+    "helpfulness_score": 5.3464285714285715,
+    "overall_score": 5.3464285714285715
+  },
+  "o4-mini-2025-04-16": {
+    "comprehension_score": 5.803571428571429,
+    "structure_score": 5.696428571428571,
+    "prose_style_score": 5.589285714285714,
+    "creativity_score": 5.442857142857143,
+    "depth_score": 5.1,
+    "helpfulness_score": 5.582142857142857,
+    "overall_score": 5.542857142857143
+  },
+  "Qwen3-235B": {
+    "comprehension_score": 5.735714285714286,
+    "structure_score": 5.875,
+    "prose_style_score": 5.628571428571429,
+    "creativity_score": 5.514285714285714,
+    "depth_score": 5.214285714285714,
+    "helpfulness_score": 5.55,
+    "overall_score": 5.5928571428571425
+  },
+  "Gemini-2.5-Flash": {
+    "comprehension_score": 6.196428571428571,
+    "structure_score": 6.2214285714285715,
+    "prose_style_score": 6.0,
+    "creativity_score": 5.828571428571428,
+    "depth_score": 5.75,
+    "helpfulness_score": 6.0321428571428575,
+    "overall_score": 6.007142857142857
+  },
+  "Qwen3-30B-A3B-Thinking": {
+    "comprehension_score": 5.914285714285715,
+    "structure_score": 6.053571428571429,
+    "prose_style_score": 6.5321428571428575,
+    "creativity_score": 6.5285714285714285,
+    "depth_score": 5.65,
+    "helpfulness_score": 5.817857142857143,
+    "overall_score": 6.064285714285714
+  },
+  "Deepseek-V3-0324": {
+    "comprehension_score": 6.082142857142857,
+    "structure_score": 6.242857142857143,
+    "prose_style_score": 6.560714285714286,
+    "creativity_score": 6.610714285714286,
+    "depth_score": 5.796428571428572,
+    "helpfulness_score": 5.957142857142857,
+    "overall_score": 6.203571428571428
+  },
+  "Qwen3-32B-Thinking": {
+    "comprehension_score": 6.339285714285714,
+    "structure_score": 6.425,
+    "prose_style_score": 7.089285714285714,
+    "creativity_score": 7.185714285714286,
+    "depth_score": 6.192857142857143,
+    "helpfulness_score": 6.182142857142857,
+    "overall_score": 6.578571428571428
+  },
+  "Qwen3-235B-Thinking": {
+    "comprehension_score": 6.385714285714286,
+    "structure_score": 6.45,
+    "prose_style_score": 7.296428571428572,
+    "creativity_score": 7.435714285714286,
+    "depth_score": 6.321428571428571,
+    "helpfulness_score": 6.285714285714286,
+    "overall_score": 6.660714285714286
+  },
+  "Deepseek-R1-0528": {
+    "comprehension_score": 6.7178571428571425,
+    "structure_score": 6.703571428571428,
+    "prose_style_score": 7.0964285714285715,
+    "creativity_score": 7.021428571428571,
+    "depth_score": 6.5964285714285715,
+    "helpfulness_score": 6.575,
+    "overall_score": 6.771428571428571
+  },
+  "o3-2025-04-16": {
+    "comprehension_score": 6.914285714285715,
+    "structure_score": 6.746428571428571,
+    "prose_style_score": 7.05,
+    "creativity_score": 6.896428571428571,
+    "depth_score": 6.439285714285714,
+    "helpfulness_score": 6.742857142857143,
+    "overall_score": 6.946428571428571
+  },
+  "gpt-5.4": {
+    "comprehension_score": 7.035714285714286,
+    "structure_score": 6.975,
+    "prose_style_score": 7.128571428571429,
+    "creativity_score": 6.9035714285714285,
+    "depth_score": 6.760714285714286,
+    "helpfulness_score": 7.025,
+    "overall_score": 7.060714285714286
+  },
+  "Gemini-3.1-Flash": {
+    "comprehension_score": 6.414285714285715,
+    "structure_score": 6.625,
+    "prose_style_score": 6.75,
+    "creativity_score": 6.660714285714286,
+    "depth_score": 6.057142857142857,
+    "helpfulness_score": 6.414285714285715,
+    "overall_score": 6.5285714285714285
+  },
+  "Gemini-3.1-Pro": {
+    "comprehension_score": 6.767857142857143,
+    "structure_score": 6.867857142857143,
+    "prose_style_score": 7.114285714285714,
+    "creativity_score": 6.875,
+    "depth_score": 6.325,
+    "helpfulness_score": 6.757142857142857,
+    "overall_score": 6.864285714285714
+  },
+  "MiniMax-M2.5": {
+    "comprehension_score": 6.364285714285714,
+    "structure_score": 6.428571428571429,
+    "prose_style_score": 6.021428571428571,
+    "creativity_score": 6.075,
+    "depth_score": 5.853571428571429,
+    "helpfulness_score": 6.275,
+    "overall_score": 6.260714285714286
+  },
+  "Qwen3.5-Plus": {
+    "comprehension_score": 6.7821428571428575,
+    "structure_score": 6.75,
+    "prose_style_score": 6.925,
+    "creativity_score": 6.735714285714286,
+    "depth_score": 6.296428571428572,
+    "helpfulness_score": 6.714285714285714,
+    "overall_score": 6.796428571428572
+  },
+  "GLM-5": {
+    "comprehension_score": 6.410714285714286,
+    "structure_score": 6.5285714285714285,
+    "prose_style_score": 6.689285714285714,
+    "creativity_score": 6.507142857142857,
+    "depth_score": 5.996428571428571,
+    "helpfulness_score": 6.360714285714286,
+    "overall_score": 6.492857142857143
+  },
+  "step-3.5-flash": {
+    "comprehension_score": 6.696428571428571,
+    "structure_score": 6.814285714285714,
+    "prose_style_score": 7.175,
+    "creativity_score": 7.260714285714286,
+    "depth_score": 6.714285714285714,
+    "helpfulness_score": 6.628571428571429,
+    "overall_score": 6.828571428571428
+  }
+}

data/complicated-writing-scores.json

@@ -0,0 +1,236 @@
+{
+  "Mistral-3.1-24B-2503": {
+    "comprehension_score": 4.518867924528302,
+    "structure_score": 4.518867924528302,
+    "prose_style_score": 3.7452830188679247,
+    "creativity_score": 3.5849056603773586,
+    "depth_score": 3.556603773584906,
+    "helpfulness_score": 4.0,
+    "overall_score": 3.9339622641509435
+  },
+  "Phi-4-14B": {
+    "comprehension_score": 4.622641509433962,
+    "structure_score": 4.688679245283019,
+    "prose_style_score": 4.09433962264151,
+    "creativity_score": 3.990566037735849,
+    "depth_score": 3.858490566037736,
+    "helpfulness_score": 4.19811320754717,
+    "overall_score": 4.10377358490566
+  },
+  "gpt-4o-mini-2024-07-18": {
+    "comprehension_score": 4.688679245283019,
+    "structure_score": 4.783018867924528,
+    "prose_style_score": 4.216981132075472,
+    "creativity_score": 4.066037735849057,
+    "depth_score": 3.792452830188679,
+    "helpfulness_score": 4.245283018867925,
+    "overall_score": 4.2075471698113205
+  },
+  "gpt-4.1-mini-2025-04-14": {
+    "comprehension_score": 4.981132075471698,
+    "structure_score": 4.877358490566038,
+    "prose_style_score": 4.509433962264151,
+    "creativity_score": 4.283018867924528,
+    "depth_score": 4.018867924528302,
+    "helpfulness_score": 4.509433962264151,
+    "overall_score": 4.330188679245283
+  },
+  "Qwen3-8B": {
+    "comprehension_score": 4.8584905660377355,
+    "structure_score": 5.018867924528302,
+    "prose_style_score": 4.556603773584905,
+    "creativity_score": 4.433962264150943,
+    "depth_score": 4.179245283018868,
+    "helpfulness_score": 4.566037735849057,
+    "overall_score": 4.462264150943396
+  },
+  "Qwen3-30B-A3B": {
+    "comprehension_score": 4.952830188679245,
+    "structure_score": 5.122641509433962,
+    "prose_style_score": 4.556603773584905,
+    "creativity_score": 4.547169811320755,
+    "depth_score": 4.283018867924528,
+    "helpfulness_score": 4.745283018867925,
+    "overall_score": 4.528301886792453
+  },
+  "gemma3-27b": {
+    "comprehension_score": 5.264150943396227,
+    "structure_score": 5.330188679245283,
+    "prose_style_score": 4.59433962264151,
+    "creativity_score": 4.820754716981132,
+    "depth_score": 4.584905660377358,
+    "helpfulness_score": 5.066037735849057,
+    "overall_score": 4.783018867924528
+  },
+  "Qwen3-32B": {
+    "comprehension_score": 5.226415094339623,
+    "structure_score": 5.386792452830188,
+    "prose_style_score": 4.915094339622642,
+    "creativity_score": 4.90566037735849,
+    "depth_score": 4.613207547169812,
+    "helpfulness_score": 5.037735849056604,
+    "overall_score": 4.80188679245283
+  },
+  "gpt-4o-2024-11-20": {
+    "comprehension_score": 5.264150943396227,
+    "structure_score": 5.320754716981132,
+    "prose_style_score": 5.066037735849057,
+    "creativity_score": 5.122641509433962,
+    "depth_score": 4.6415094339622645,
+    "helpfulness_score": 4.990566037735849,
+    "overall_score": 4.943396226415095
+  },
+  "Mistral-3.2-24B-2506": {
+    "comprehension_score": 5.4245283018867925,
+    "structure_score": 5.622641509433962,
+    "prose_style_score": 5.1415094339622645,
+    "creativity_score": 5.481132075471698,
+    "depth_score": 4.688679245283019,
+    "helpfulness_score": 5.113207547169812,
+    "overall_score": 5.056603773584905
+  },
+  "o4-mini-2025-04-16": {
+    "comprehension_score": 5.509433962264151,
+    "structure_score": 5.481132075471698,
+    "prose_style_score": 5.330188679245283,
+    "creativity_score": 5.264150943396227,
+    "depth_score": 4.7924528301886795,
+    "helpfulness_score": 5.235849056603773,
+    "overall_score": 5.132075471698113
+  },
+  "Qwen3-235B": {
+    "comprehension_score": 5.7075471698113205,
+    "structure_score": 5.811320754716981,
+    "prose_style_score": 5.367924528301887,
+    "creativity_score": 5.5,
+    "depth_score": 5.0754716981132075,
+    "helpfulness_score": 5.452830188679245,
+    "overall_score": 5.415094339622642
+  },
+  "Gemini-2.5-Flash": {
+    "comprehension_score": 6.19811320754717,
+    "structure_score": 6.1415094339622645,
+    "prose_style_score": 5.9245283018867925,
+    "creativity_score": 5.80188679245283,
+    "depth_score": 5.7075471698113205,
+    "helpfulness_score": 6.0,
+    "overall_score": 5.943396226415095
+  },
+  "Qwen3-30B-A3B-Thinking": {
+    "comprehension_score": 5.773584905660377,
+    "structure_score": 6.047169811320755,
+    "prose_style_score": 6.547169811320755,
+    "creativity_score": 6.735849056603773,
+    "depth_score": 5.669811320754717,
+    "helpfulness_score": 5.783018867924528,
+    "overall_score": 6.028301886792453
+  },
+  "Deepseek-V3-0324": {
+    "comprehension_score": 6.113207547169812,
+    "structure_score": 6.122641509433962,
+    "prose_style_score": 6.547169811320755,
+    "creativity_score": 6.820754716981132,
+    "depth_score": 5.820754716981132,
+    "helpfulness_score": 5.8584905660377355,
+    "overall_score": 6.150943396226415
+  },
+  "Qwen3-32B-Thinking": {
+    "comprehension_score": 6.2075471698113205,
+    "structure_score": 6.216981132075472,
+    "prose_style_score": 7.150943396226415,
+    "creativity_score": 7.443396226415095,
+    "depth_score": 6.179245283018868,
+    "helpfulness_score": 6.09433962264151,
+    "overall_score": 6.547169811320755
+  },
+  "Qwen3-235B-Thinking": {
+    "comprehension_score": 6.216981132075472,
+    "structure_score": 6.254716981132075,
+    "prose_style_score": 7.4245283018867925,
+    "creativity_score": 7.773584905660377,
+    "depth_score": 6.320754716981132,
+    "helpfulness_score": 6.169811320754717,
+    "overall_score": 6.584905660377358
+  },
+  "Deepseek-R1-0528": {
+    "comprehension_score": 6.773584905660377,
+    "structure_score": 6.735849056603773,
+    "prose_style_score": 7.320754716981132,
+    "creativity_score": 7.367924528301887,
+    "depth_score": 6.849056603773585,
+    "helpfulness_score": 6.726415094339623,
+    "overall_score": 6.9245283018867925
+  },
+  "o3-2025-04-16": {
+    "comprehension_score": 7.226415094339623,
+    "structure_score": 7.018867924528302,
+    "prose_style_score": 7.452830188679245,
+    "creativity_score": 7.2924528301886795,
+    "depth_score": 6.688679245283019,
+    "helpfulness_score": 6.915094339622642,
+    "overall_score": 7.179245283018868
+  },
+  "gpt-5.4": {
+    "comprehension_score": 7.023529411764706,
+    "structure_score": 6.870588235294117,
+    "prose_style_score": 7.311764705882353,
+    "creativity_score": 6.947058823529412,
+    "depth_score": 6.8882352941176475,
+    "helpfulness_score": 6.9,
+    "overall_score": 7.052941176470588
+  },
+  "Gemini-3.1-Flash": {
+    "comprehension_score": 6.211764705882353,
+    "structure_score": 6.411764705882353,
+    "prose_style_score": 6.711764705882353,
+    "creativity_score": 6.511764705882353,
+    "depth_score": 5.8882352941176475,
+    "helpfulness_score": 6.123529411764705,
+    "overall_score": 6.341176470588235
+  },
+  "Gemini-3.1-Pro": {
+    "comprehension_score": 6.58235294117647,
+    "structure_score": 6.635294117647059,
+    "prose_style_score": 7.1117647058823525,
+    "creativity_score": 6.735294117647059,
+    "depth_score": 6.2,
+    "helpfulness_score": 6.488235294117647,
+    "overall_score": 6.7176470588235295
+  },
+  "MiniMax-M2.5": {
+    "comprehension_score": 6.205882352941177,
+    "structure_score": 6.2,
+    "prose_style_score": 5.9,
+    "creativity_score": 5.9941176470588236,
+    "depth_score": 5.694117647058824,
+    "helpfulness_score": 6.011764705882353,
+    "overall_score": 6.035294117647059
+  },
+  "Qwen3.5-Plus": {
+    "comprehension_score": 6.594117647058823,
+    "structure_score": 6.488235294117647,
+    "prose_style_score": 6.982352941176471,
+    "creativity_score": 6.629411764705883,
+    "depth_score": 6.135294117647059,
+    "helpfulness_score": 6.405882352941177,
+    "overall_score": 6.605882352941176
+  },
+  "GLM-5": {
+    "comprehension_score": 6.2176470588235295,
+    "structure_score": 6.3352941176470585,
+    "prose_style_score": 6.658823529411765,
+    "creativity_score": 6.411764705882353,
+    "depth_score": 5.882352941176471,
+    "helpfulness_score": 6.1117647058823525,
+    "overall_score": 6.323529411764706
+  },
+  "step-3.5-flash": {
+    "comprehension_score": 6.6,
+    "structure_score": 6.682352941176471,
+    "prose_style_score": 7.2,
+    "creativity_score": 7.288235294117647,
+    "depth_score": 6.670588235294118,
+    "helpfulness_score": 6.458823529411765,
+    "overall_score": 6.723529411764706
+  }
+}

data/gpt5.4-judge-all-scores.json

@@ -0,0 +1,236 @@
+{
+  "o3-2025-04-16": {
+    "comprehension_score": 7.389285714285714,
+    "structure_score": 7.417857142857143,
+    "prose_style_score": 7.575,
+    "creativity_score": 7.564285714285714,
+    "depth_score": 7.196428571428571,
+    "helpfulness_score": 7.357142857142857,
+    "overall_score": 7.307142857142857
+  },
+  "Deepseek-R1-0528": {
+    "comprehension_score": 7.146428571428571,
+    "structure_score": 7.0964285714285715,
+    "prose_style_score": 7.085714285714285,
+    "creativity_score": 7.5964285714285715,
+    "depth_score": 7.4,
+    "helpfulness_score": 7.053571428571429,
+    "overall_score": 7.139285714285714
+  },
+  "Deepseek-V3-0324": {
+    "comprehension_score": 6.453571428571428,
+    "structure_score": 6.578571428571428,
+    "prose_style_score": 6.832142857142857,
+    "creativity_score": 7.142857142857143,
+    "depth_score": 6.353571428571429,
+    "helpfulness_score": 6.364285714285714,
+    "overall_score": 6.457142857142857
+  },
+  "Qwen3-235B-Thinking": {
+    "comprehension_score": 6.4071428571428575,
+    "structure_score": 6.446428571428571,
+    "prose_style_score": 7.2214285714285715,
+    "creativity_score": 7.75,
+    "depth_score": 6.739285714285714,
+    "helpfulness_score": 6.239285714285714,
+    "overall_score": 6.517857142857143
+  },
+  "Qwen3-32B-Thinking": {
+    "comprehension_score": 6.457142857142857,
+    "structure_score": 6.4714285714285715,
+    "prose_style_score": 7.128571428571429,
+    "creativity_score": 7.525,
+    "depth_score": 6.614285714285714,
+    "helpfulness_score": 6.317857142857143,
+    "overall_score": 6.546428571428572
+  },
+  "Qwen3-30B-A3B-Thinking": {
+    "comprehension_score": 5.964285714285714,
+    "structure_score": 6.110714285714286,
+    "prose_style_score": 6.521428571428571,
+    "creativity_score": 6.8428571428571425,
+    "depth_score": 5.985714285714286,
+    "helpfulness_score": 5.882142857142857,
+    "overall_score": 6.010714285714286
+  },
+  "Gemini-2.5-Flash": {
+    "comprehension_score": 6.503571428571429,
+    "structure_score": 6.571428571428571,
+    "prose_style_score": 5.942857142857143,
+    "creativity_score": 6.228571428571429,
+    "depth_score": 6.257142857142857,
+    "helpfulness_score": 6.428571428571429,
+    "overall_score": 6.2785714285714285
+  },
+  "Qwen3-235B": {
+    "comprehension_score": 5.896428571428571,
+    "structure_score": 6.2,
+    "prose_style_score": 5.667857142857143,
+    "creativity_score": 5.785714285714286,
+    "depth_score": 5.503571428571429,
+    "helpfulness_score": 5.8464285714285715,
+    "overall_score": 5.767857142857143
+  },
+  "Qwen3-32B": {
+    "comprehension_score": 5.303571428571429,
+    "structure_score": 5.582142857142857,
+    "prose_style_score": 4.960714285714285,
+    "creativity_score": 5.189285714285714,
+    "depth_score": 4.896428571428571,
+    "helpfulness_score": 5.117857142857143,
+    "overall_score": 5.042857142857143
+  },
+  "Qwen3-8B": {
+    "comprehension_score": 4.860714285714286,
+    "structure_score": 5.0928571428571425,
+    "prose_style_score": 4.55,
+    "creativity_score": 4.710714285714285,
+    "depth_score": 4.457142857142857,
+    "helpfulness_score": 4.639285714285714,
+    "overall_score": 4.560714285714286
+  },
+  "Qwen3-30B-A3B": {
+    "comprehension_score": 4.953571428571428,
+    "structure_score": 5.2214285714285715,
+    "prose_style_score": 4.6,
+    "creativity_score": 4.7785714285714285,
+    "depth_score": 4.521428571428571,
+    "helpfulness_score": 4.760714285714286,
+    "overall_score": 4.65
+  },
+  "gemma3-27b": {
+    "comprehension_score": 5.164285714285715,
+    "structure_score": 5.364285714285714,
+    "prose_style_score": 4.553571428571429,
+    "creativity_score": 5.064285714285714,
+    "depth_score": 4.710714285714285,
+    "helpfulness_score": 4.992857142857143,
+    "overall_score": 4.814285714285714
+  },
+  "Phi-4-14B": {
+    "comprehension_score": 4.2785714285714285,
+    "structure_score": 4.514285714285714,
+    "prose_style_score": 3.7714285714285714,
+    "creativity_score": 4.310714285714286,
+    "depth_score": 4.0285714285714285,
+    "helpfulness_score": 4.017857142857143,
+    "overall_score": 3.9857142857142858
+  },
+  "Mistral-3.2-24B-2506": {
+    "comprehension_score": 5.475,
+    "structure_score": 5.746428571428571,
+    "prose_style_score": 5.35,
+    "creativity_score": 5.885714285714286,
+    "depth_score": 5.214285714285714,
+    "helpfulness_score": 5.3464285714285715,
+    "overall_score": 5.335714285714285
+  },
+  "Mistral-3.1-24B-2503": {
+    "comprehension_score": 4.303571428571429,
+    "structure_score": 4.521428571428571,
+    "prose_style_score": 3.6857142857142855,
+    "creativity_score": 3.9642857142857144,
+    "depth_score": 3.8285714285714287,
+    "helpfulness_score": 4.021428571428571,
+    "overall_score": 3.9214285714285713
+  },
+  "gpt-4o-2024-11-20": {
+    "comprehension_score": 5.275,
+    "structure_score": 5.239285714285714,
+    "prose_style_score": 4.996428571428571,
+    "creativity_score": 5.321428571428571,
+    "depth_score": 4.892857142857143,
+    "helpfulness_score": 4.957142857142857,
+    "overall_score": 4.985714285714286
+  },
+  "gpt-4.1-mini-2025-04-14": {
+    "comprehension_score": 4.8,
+    "structure_score": 4.746428571428571,
+    "prose_style_score": 4.339285714285714,
+    "creativity_score": 4.489285714285714,
+    "depth_score": 4.275,
+    "helpfulness_score": 4.389285714285714,
+    "overall_score": 4.35
+  },
+  "gpt-4o-mini-2024-07-18": {
+    "comprehension_score": 4.417857142857143,
+    "structure_score": 4.575,
+    "prose_style_score": 4.064285714285714,
+    "creativity_score": 4.375,
+    "depth_score": 4.085714285714285,
+    "helpfulness_score": 4.139285714285714,
+    "overall_score": 4.15
+  },
+  "o4-mini-2025-04-16": {
+    "comprehension_score": 5.803571428571429,
+    "structure_score": 5.864285714285714,
+    "prose_style_score": 5.428571428571429,
+    "creativity_score": 5.760714285714286,
+    "depth_score": 5.310714285714286,
+    "helpfulness_score": 5.617857142857143,
+    "overall_score": 5.557142857142857
+  },
+  "gpt-5.4": {
+    "comprehension_score": 7.4678571428571425,
+    "structure_score": 7.517857142857143,
+    "prose_style_score": 7.585714285714285,
+    "creativity_score": 7.182142857142857,
+    "depth_score": 7.5,
+    "helpfulness_score": 7.664285714285715,
+    "overall_score": 7.421428571428572
+  },
+  "Gemini-3.1-Flash": {
+    "comprehension_score": 7.0964285714285715,
+    "structure_score": 7.232142857142857,
+    "prose_style_score": 7.317857142857143,
+    "creativity_score": 7.417857142857143,
+    "depth_score": 7.053571428571429,
+    "helpfulness_score": 7.185714285714286,
+    "overall_score": 7.117857142857143
+  },
+  "Gemini-3.1-Pro": {
+    "comprehension_score": 7.510714285714286,
+    "structure_score": 7.5321428571428575,
+    "prose_style_score": 7.5285714285714285,
+    "creativity_score": 7.614285714285714,
+    "depth_score": 7.321428571428571,
+    "helpfulness_score": 7.65,
+    "overall_score": 7.460714285714285
+  },
+  "MiniMax-M2.5": {
+    "comprehension_score": 6.292857142857143,
+    "structure_score": 6.442857142857143,
+    "prose_style_score": 5.614285714285714,
+    "creativity_score": 6.171428571428572,
+    "depth_score": 5.975,
+    "helpfulness_score": 6.242857142857143,
+    "overall_score": 6.071428571428571
+  },
+  "Qwen3.5-Plus": {
+    "comprehension_score": 7.228571428571429,
+    "structure_score": 7.3,
+    "prose_style_score": 7.232142857142857,
+    "creativity_score": 7.353571428571429,
+    "depth_score": 7.196428571428571,
+    "helpfulness_score": 7.289285714285715,
+    "overall_score": 7.189285714285714
+  },
+  "step-3.5-flash": {
+    "comprehension_score": 7.285714285714286,
+    "structure_score": 7.335714285714285,
+    "prose_style_score": 7.053571428571429,
+    "creativity_score": 7.789285714285715,
+    "depth_score": 7.525,
+    "helpfulness_score": 7.2178571428571425,
+    "overall_score": 7.253571428571429
+  },
+  "GLM-5": {
+    "comprehension_score": 7.103571428571429,
+    "structure_score": 7.182142857142857,
+    "prose_style_score": 7.114285714285714,
+    "creativity_score": 7.185714285714286,
+    "depth_score": 6.964285714285714,
+    "helpfulness_score": 7.146428571428571,
+    "overall_score": 7.042857142857143
+  }
+}

data/gpt5.4-judge-complicated-writing-scores.json

@@ -0,0 +1,236 @@
+{
+  "o3-2025-04-16": {
+    "comprehension_score": 7.5,
+    "structure_score": 7.541176470588235,
+    "prose_style_score": 7.788235294117647,
+    "creativity_score": 7.688235294117647,
+    "depth_score": 7.358823529411764,
+    "helpfulness_score": 7.476470588235294,
+    "overall_score": 7.4411764705882355
+  },
+  "Deepseek-R1-0528": {
+    "comprehension_score": 7.070588235294117,
+    "structure_score": 7.0,
+    "prose_style_score": 7.352941176470588,
+    "creativity_score": 7.647058823529412,
+    "depth_score": 7.341176470588235,
+    "helpfulness_score": 6.923529411764706,
+    "overall_score": 7.105882352941176
+  },
+  "Deepseek-V3-0324": {
+    "comprehension_score": 6.188235294117647,
+    "structure_score": 6.3,
+    "prose_style_score": 6.758823529411765,
+    "creativity_score": 7.0588235294117645,
+    "depth_score": 6.223529411764706,
+    "helpfulness_score": 6.035294117647059,
+    "overall_score": 6.223529411764706
+  },
+  "Qwen3-235B-Thinking": {
+    "comprehension_score": 6.376470588235295,
+    "structure_score": 6.252941176470588,
+    "prose_style_score": 7.435294117647059,
+    "creativity_score": 7.829411764705882,
+    "depth_score": 6.7176470588235295,
+    "helpfulness_score": 6.176470588235294,
+    "overall_score": 6.517647058823529
+  },
+  "Qwen3-32B-Thinking": {
+    "comprehension_score": 6.3882352941176475,
+    "structure_score": 6.323529411764706,
+    "prose_style_score": 7.323529411764706,
+    "creativity_score": 7.570588235294117,
+    "depth_score": 6.523529411764706,
+    "helpfulness_score": 6.258823529411765,
+    "overall_score": 6.523529411764706
+  },
+  "Qwen3-30B-A3B-Thinking": {
+    "comprehension_score": 5.823529411764706,
+    "structure_score": 5.952941176470588,
+    "prose_style_score": 6.570588235294117,
+    "creativity_score": 6.829411764705882,
+    "depth_score": 5.7823529411764705,
+    "helpfulness_score": 5.735294117647059,
+    "overall_score": 5.876470588235295
+  },
+  "Gemini-2.5-Flash": {
+    "comprehension_score": 6.429411764705883,
+    "structure_score": 6.482352941176471,
+    "prose_style_score": 5.847058823529411,
+    "creativity_score": 6.147058823529412,
+    "depth_score": 6.094117647058823,
+    "helpfulness_score": 6.2823529411764705,
+    "overall_score": 6.147058823529412
+  },
+  "Qwen3-235B": {
+    "comprehension_score": 5.788235294117647,
+    "structure_score": 6.070588235294117,
+    "prose_style_score": 5.511764705882353,
+    "creativity_score": 5.647058823529412,
+    "depth_score": 5.4,
+    "helpfulness_score": 5.623529411764705,
+    "overall_score": 5.58235294117647
+  },
+  "Qwen3-32B": {
+    "comprehension_score": 5.117647058823529,
+    "structure_score": 5.364705882352941,
+    "prose_style_score": 4.694117647058824,
+    "creativity_score": 4.982352941176471,
+    "depth_score": 4.647058823529412,
+    "helpfulness_score": 4.794117647058823,
+    "overall_score": 4.729411764705882
+  },
+  "Qwen3-8B": {
+    "comprehension_score": 4.6647058823529415,
+    "structure_score": 4.870588235294117,
+    "prose_style_score": 4.2823529411764705,
+    "creativity_score": 4.5,
+    "depth_score": 4.241176470588235,
+    "helpfulness_score": 4.347058823529411,
+    "overall_score": 4.3
+  },
+  "Qwen3-30B-A3B": {
+    "comprehension_score": 4.805882352941176,
+    "structure_score": 4.988235294117647,
+    "prose_style_score": 4.405882352941177,
+    "creativity_score": 4.617647058823529,
+    "depth_score": 4.364705882352941,
+    "helpfulness_score": 4.523529411764706,
+    "overall_score": 4.429411764705883
+  },
+  "gemma3-27b": {
+    "comprehension_score": 5.070588235294117,
+    "structure_score": 5.241176470588235,
+    "prose_style_score": 4.470588235294118,
+    "creativity_score": 5.011764705882353,
+    "depth_score": 4.58235294117647,
+    "helpfulness_score": 4.817647058823529,
+    "overall_score": 4.6647058823529415
+  },
+  "Phi-4-14B": {
+    "comprehension_score": 4.235294117647059,
+    "structure_score": 4.529411764705882,
+    "prose_style_score": 3.652941176470588,
+    "creativity_score": 4.258823529411765,
+    "depth_score": 4.023529411764706,
+    "helpfulness_score": 4.017647058823529,
+    "overall_score": 3.9647058823529413
+  },
+  "Mistral-3.2-24B-2506": {
+    "comprehension_score": 5.3352941176470585,
+    "structure_score": 5.570588235294117,
+    "prose_style_score": 5.188235294117647,
+    "creativity_score": 5.7176470588235295,
+    "depth_score": 5.047058823529412,
+    "helpfulness_score": 5.147058823529412,
+    "overall_score": 5.147058823529412
+  },
+  "Mistral-3.1-24B-2503": {
+    "comprehension_score": 4.276470588235294,
+    "structure_score": 4.523529411764706,
+    "prose_style_score": 3.523529411764706,
+    "creativity_score": 3.9411764705882355,
+    "depth_score": 3.8117647058823527,
+    "helpfulness_score": 4.029411764705882,
+    "overall_score": 3.9058823529411764
+  },
+  "gpt-4o-2024-11-20": {
+    "comprehension_score": 5.223529411764706,
+    "structure_score": 5.176470588235294,
+    "prose_style_score": 4.882352941176471,
+    "creativity_score": 5.211764705882353,
+    "depth_score": 4.788235294117647,
+    "helpfulness_score": 4.852941176470588,
+    "overall_score": 4.858823529411764
+  },
+  "gpt-4.1-mini-2025-04-14": {
+    "comprehension_score": 4.7,
+    "structure_score": 4.694117647058824,
+    "prose_style_score": 4.247058823529412,
+    "creativity_score": 4.405882352941177,
+    "depth_score": 4.176470588235294,
+    "helpfulness_score": 4.264705882352941,
+    "overall_score": 4.241176470588235
+  },
+  "gpt-4o-mini-2024-07-18": {
+    "comprehension_score": 4.41764705882353,
+    "structure_score": 4.588235294117647,
+    "prose_style_score": 4.0,
+    "creativity_score": 4.329411764705882,
+    "depth_score": 4.076470588235294,
+    "helpfulness_score": 4.117647058823529,
+    "overall_score": 4.147058823529412
+  },
+  "o4-mini-2025-04-16": {
+    "comprehension_score": 5.694117647058824,
+    "structure_score": 5.764705882352941,
+    "prose_style_score": 5.341176470588235,
+    "creativity_score": 5.623529411764705,
+    "depth_score": 5.152941176470589,
+    "helpfulness_score": 5.488235294117647,
+    "overall_score": 5.41764705882353
+  },
+  "gpt-5.4": {
+    "comprehension_score": 7.529411764705882,
+    "structure_score": 7.535294117647059,
+    "prose_style_score": 7.858823529411764,
+    "creativity_score": 7.3,
+    "depth_score": 7.7176470588235295,
+    "helpfulness_score": 7.5588235294117645,
+    "overall_score": 7.482352941176471
+  },
+  "Gemini-3.1-Flash": {
+    "comprehension_score": 7.041176470588235,
+    "structure_score": 7.1647058823529415,
+    "prose_style_score": 7.411764705882353,
+    "creativity_score": 7.294117647058823,
+    "depth_score": 7.0,
+    "helpfulness_score": 7.064705882352941,
+    "overall_score": 7.064705882352941
+  },
+  "Gemini-3.1-Pro": {
+    "comprehension_score": 7.511764705882353,
+    "structure_score": 7.5,
+    "prose_style_score": 7.682352941176471,
+    "creativity_score": 7.5,
+    "depth_score": 7.305882352941176,
+    "helpfulness_score": 7.552941176470588,
+    "overall_score": 7.452941176470588
+  },
+  "MiniMax-M2.5": {
+    "comprehension_score": 6.176470588235294,
+    "structure_score": 6.323529411764706,
+    "prose_style_score": 5.511764705882353,
+    "creativity_score": 6.011764705882353,
+    "depth_score": 5.788235294117647,
+    "helpfulness_score": 6.035294117647059,
+    "overall_score": 5.905882352941177
+  },
+  "Qwen3.5-Plus": {
+    "comprehension_score": 7.205882352941177,
+    "structure_score": 7.2823529411764705,
+    "prose_style_score": 7.41764705882353,
+    "creativity_score": 7.394117647058824,
+    "depth_score": 7.205882352941177,
+    "helpfulness_score": 7.229411764705882,
+    "overall_score": 7.2
+  },
+  "step-3.5-flash": {
+    "comprehension_score": 7.258823529411765,
+    "structure_score": 7.252941176470588,
+    "prose_style_score": 7.105882352941176,
+    "creativity_score": 7.8352941176470585,
+    "depth_score": 7.552941176470588,
+    "helpfulness_score": 7.1647058823529415,
+    "overall_score": 7.229411764705882
+  },
+  "GLM-5": {
+    "comprehension_score": 7.064705882352941,
+    "structure_score": 7.147058823529412,
+    "prose_style_score": 7.176470588235294,
+    "creativity_score": 7.1,
+    "depth_score": 6.8882352941176475,
+    "helpfulness_score": 7.064705882352941,
+    "overall_score": 7.011764705882353
+  }
+}

index.html

@@ -0,0 +1,101 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Zhiyin</title>
+    <link rel="stylesheet" href="styles.css">
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">
+</head>
+<body>
+    <div class="container">
+        <header class="header">
+            <h1><i class="fas fa-feather"></i> Zhiyin</h1>
+            <p>Exploring the Frontier of Chinese LLM Writing</p>
+        </header>
+
+        <div class="dashboard card">
+            <section class="overview-section">
+                <h2 class="section-title">
+                  <span class="accent-bar"></span>
+                  Benchmark Overview
+                  <span class="section-title-spacer"></span>
+                  <span class="external-links-text">
+                    <a href="https://github.com/zake7749/Chinese-Writing-Bench" target="_blank" rel="noopener" class="external-link-text">GitHub</a>
+                    <span class="divider">&bull;</span>
+                    <a href="https://huggingface.co/datasets/zake7749/chinese-writing-benchmark" target="_blank" rel="noopener" class="external-link-text">Hugging Face</a>
+                  </span>
+                </h2>
+                <div class="overview-content">
+                    <div class="overview-text">
+                        <p>
+                          <strong>Zhiyin</strong> is an LLM-as-a-judge benchmark for Chinese writing evaluation, featuring 280 test cases across 18 diverse writing tasks in this V1 release.
+                        </p>
+                        <p>
+                            Our method relies on <strong>pairwise comparison</strong>. A powerful language model acts as the judge, scoring a model's response relative to a fixed baseline (GPT-4.1), which is anchored at a score of 5.
+                        </p>
+                
+                        <h4>Scoring System</h4>
+                        <p>The judge assigns the model's response an integer score from 0 to 10, where:</p>
+                        <ul>
+                            <li>A score > 5 indicates the response is <strong>superior</strong> to the baseline.</li>
+                            <li>A score = 5 indicates the response is <strong>on par</strong> with the baseline.</li>
+                            <li>A score < 5 indicates the response is <strong>inferior</strong> to the baseline.</li>
+                        </ul>
+                
+                        <h4>Evaluation Dimensions</h4>
+                        <p>To ensure a comprehensive analysis, the final score is informed by a multi-dimensional assessment. The judge evaluates the response across six key criteria:</p>
+                        <ol>
+                            <li><strong>Comprehension & Relevance:</strong> How well the response understands the prompt's intent and stays on topic.</li>
+                            <li><strong>Structure & Coherence:</strong> How clear, logical, and well-organized the writing is.</li>
+                            <li><strong>Prose & Style:</strong> The quality of the language, grammar, and adherence to the requested tone.</li>
+                            <li><strong>Creativity & Originality:</strong> The novelty of the ideas and the uniqueness of the perspective.</li>
+                            <li><strong>Depth & Insight:</strong> The level of detail, analysis, and substance provided.</li>
+                            <li><strong>Helpfulness:</strong> How effectively the response fulfills the user's overall goal.</li>
+                        </ol>
+                    </div>
+                </div>
+            </section>
+
+            <section class="judge-section">
+                <h2 class="section-title"><span class="accent-bar"></span>Judge Model</h2>
+                <div class="judge-toggle">
+                    <button class="judge-btn active" data-judge="o3">O3</button>
+                    <button class="judge-btn" data-judge="gpt5.4">GPT-5.4</button>
+                </div>
+            </section>
+
+            <section class="table-section">
+                <h2 class="section-title"><span class="accent-bar"></span>All Writing Tasks</h2>
+                <div id="generalTable" class="table-container">
+                    <!-- General Writing table will be populated here -->
+                </div>
+            </section>
+
+            <section class="table-section">
+                <h2 class="section-title"><span class="accent-bar"></span>Complicated Writing Tasks</h2>
+                <div id="complicatedTable" class="table-container">
+                    <!-- Complicated Writing table will be populated here -->
+                </div>
+            </section>
+
+            <section class="citation-section">
+                <h2 class="section-title"><span class="accent-bar"></span>Citation</h2>
+                <div class="citation-content">
+                    <p>
+                        If you use these results, please cite our paper:<br>
+                        <em>"Zhiyin: Exploring the Frontier of Chinese LLM Writing, 2025. https://github.com/zake7749/Chinese-Writing-Bench"</em>
+                    </p>
+                </div>
+            </section>
+        </div>
+
+        <div id="loading" class="loading">
+            <div class="spinner"></div>
+            <p>Loading benchmark data...</p>
+        </div>
+    </div>
+    <script src="script.js"></script>
+</body>
+</html> 

script.js

@@ -0,0 +1,206 @@
+class LLMBenchmarkDashboard {
+    constructor() {
+        this.currentJudge = 'o3';
+        this.judgeData = {
+            o3: { general: null, complicated: null },
+            'gpt5.4': { general: null, complicated: null }
+        };
+        this.generalSort = { column: 'overall_score', direction: 'desc' };
+        this.complicatedSort = { column: 'overall_score', direction: 'desc' };
+        this.metricDisplayNames = {
+            comprehension_score: 'Comprehension',
+            structure_score: 'Coherence',
+            prose_style_score: 'Style',
+            creativity_score: 'Creativity',
+            depth_score: 'Depth',
+            helpfulness_score: 'Helpfulness',
+            overall_score: 'Overall'
+        };
+        this.judgePaths = {
+            o3: {
+                general: 'data/all-scores.json',
+                complicated: 'data/complicated-writing-scores.json'
+            },
+            'gpt5.4': {
+                general: 'data/gpt5.4-judge-all-scores.json',
+                complicated: 'data/gpt5.4-judge-complicated-writing-scores.json'
+            }
+        };
+        this.modelLinks = {
+            'Monomer-24B-Writer': 'https://huggingface.co/zake7749/Monomer-24B-Writer-Preview',
+            'Monomer-8B-Writer': 'https://huggingface.co/zake7749/Monomer-8B-Writer-Preview'
+        };
+        this.init();
+    }
+
+    async init() {
+        this.showLoading(true);
+        const promises = [];
+        for (const judge of ['o3', 'gpt5.4']) {
+            for (const type of ['general', 'complicated']) {
+                promises.push(this.loadData(this.judgePaths[judge][type], judge, type));
+            }
+        }
+        await Promise.all(promises);
+        this.renderTable('general');
+        this.renderTable('complicated');
+        this.setupJudgeToggle();
+        this.showLoading(false);
+    }
+
+    async loadData(path, judge, type) {
+        try {
+            const response = await fetch(path);
+            if (!response.ok) {
+                throw new Error(`HTTP error! status: ${response.status}`);
+            }
+            this.judgeData[judge][type] = await response.json();
+        } catch (error) {
+            console.error(`Error loading ${judge}/${type} data:`, error);
+        }
+    }
+
+    get generalData() {
+        return this.judgeData[this.currentJudge].general;
+    }
+
+    get complicatedData() {
+        return this.judgeData[this.currentJudge].complicated;
+    }
+
+    setupJudgeToggle() {
+        const buttons = document.querySelectorAll('.judge-btn');
+        buttons.forEach(btn => {
+            btn.addEventListener('click', () => {
+                const judge = btn.dataset.judge;
+                if (judge === this.currentJudge) return;
+
+                this.currentJudge = judge;
+                buttons.forEach(b => b.classList.remove('active'));
+                btn.classList.add('active');
+
+                this.renderTable('general');
+                this.renderTable('complicated');
+            });
+        });
+    }
+
+    renderTable(type) {
+        const data = type === 'general' ? this.generalData : this.complicatedData;
+        const sortState = type === 'general' ? this.generalSort : this.complicatedSort;
+        const tableContainer = document.getElementById(type === 'general' ? 'generalTable' : 'complicatedTable');
+        if (!data) return;
+
+        const models = Object.keys(data);
+        const metrics = Object.keys(data[models[0]]);
+
+        const tableHTML = `
+            <table>
+                <thead>
+                    <tr>
+                        <th class="sortable${sortState.column === 'model' ? ' sort-' + sortState.direction : ''}" data-type="${type}" data-column="model">Model</th>
+                        ${metrics.map(metric => `
+                            <th class="sortable${sortState.column === metric ? ' sort-' + sortState.direction : ''}" data-type="${type}" data-column="${metric}">${this.metricDisplayNames[metric] || metric}</th>
+                        `).join('')}
+                    </tr>
+                </thead>
+                <tbody>
+                    ${this.getSortedTableData(data, sortState, metrics).map(row => {
+                        const isMonomer = this.modelLinks[row.model];
+                        return `
+                        <tr${isMonomer ? ' class="highlight-row"' : ''}>
+                            <td class="model-cell">${isMonomer ? `<a href="${this.modelLinks[row.model]}" target="_blank" rel="noopener" class="model-link">${row.model}</a>` : row.model}</td>
+                            ${metrics.map(metric => `
+                                <td class="score-cell">${this.formatScore(row[metric])}</td>
+                            `).join('')}
+                        </tr>
+                    `;
+                    }).join('')}
+                </tbody>
+            </table>
+        `;
+
+        tableContainer.innerHTML = tableHTML;
+        this.setupTableSorting(type);
+    }
+
+    getSortedTableData(data, sortState, metrics) {
+        const models = Object.keys(data);
+        let tableData = models.map(model => ({
+            model,
+            ...data[model]
+        }));
+
+        if (sortState.column) {
+            tableData.sort((a, b) => {
+                let aVal = a[sortState.column];
+                let bVal = b[sortState.column];
+                if (sortState.column === 'model') {
+                    aVal = aVal.toLowerCase();
+                    bVal = bVal.toLowerCase();
+                }
+                if (aVal < bVal) return sortState.direction === 'asc' ? -1 : 1;
+                if (aVal > bVal) return sortState.direction === 'asc' ? 1 : -1;
+                return 0;
+            });
+        }
+        return tableData;
+    }
+
+    formatScore(value) {
+        if (typeof value === 'number') {
+            return value.toFixed(2);
+        }
+        return value;
+    }
+
+    setupTableSorting(type) {
+        const tableContainer = document.getElementById(type === 'general' ? 'generalTable' : 'complicatedTable');
+        const headers = tableContainer.querySelectorAll('th.sortable');
+        headers.forEach(header => {
+            header.addEventListener('click', () => {
+                const column = header.dataset.column;
+                this.handleSort(type, column, header);
+            });
+        });
+    }
+
+    handleSort(type, column, headerElement) {
+        const sortState = type === 'general' ? this.generalSort : this.complicatedSort;
+        if (sortState.column === column) {
+            sortState.direction = sortState.direction === 'asc' ? 'desc' : 'asc';
+        } else {
+            sortState.column = column;
+            sortState.direction = 'asc';
+        }
+        const tableContainer = document.getElementById(type === 'general' ? 'generalTable' : 'complicatedTable');
+        tableContainer.querySelectorAll('th.sortable').forEach(th => {
+            th.classList.remove('sort-asc', 'sort-desc');
+        });
+        headerElement.classList.add(`sort-${sortState.direction}`);
+        this.renderTable(type);
+    }
+
+    showLoading(show) {
+        const loading = document.getElementById('loading');
+        if (show) {
+            loading.classList.remove('hidden');
+        } else {
+            loading.classList.add('hidden');
+        }
+    }
+
+    showError(message) {
+        const loading = document.getElementById('loading');
+        loading.innerHTML = `
+            <div class="no-data">
+                <i class="fas fa-exclamation-triangle"></i>
+                <p>${message}</p>
+            </div>
+        `;
+    }
+}
+
+document.addEventListener('DOMContentLoaded', () => {
+    new LLMBenchmarkDashboard();
+});

styles.css

@@ -0,0 +1,458 @@
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+}
+
+body {
+    font-family: 'Inter', sans-serif;
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    min-height: 100vh;
+    color: #333;
+}
+
+.container {
+    max-width: 1400px;
+    margin: 0 auto;
+    padding: 20px;
+}
+
+.header {
+    text-align: center;
+    margin-bottom: 24px;
+    color: white;
+    padding: 48px 0 36px 0;
+    position: relative;
+    background: none;
+    box-shadow: 0 2px 12px 0 rgba(76, 75, 162, 0.06);
+}
+
+.header h1 {
+    font-size: 3.2rem;
+    font-weight: 800;
+    margin-bottom: 18px;
+    letter-spacing: 0.12em;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    gap: 18px;
+}
+
+.header h1 .fas {
+    font-size: 2.2rem;
+    background: linear-gradient(135deg, #764ba2 60%, #667eea 100%);
+    color: white;
+    border-radius: 50%;
+    padding: 16px 18px;
+    box-shadow: 0 2px 12px #764ba244;
+    vertical-align: middle;
+}
+
+.header p {
+    font-size: 1.25rem;
+    font-weight: 400;
+    color: #ece6fa;
+    opacity: 0.92;
+    margin-top: 0;
+    margin-bottom: 0;
+    letter-spacing: 0.04em;
+}
+
+.card {
+    background: white;
+    border-radius: 16px;
+    box-shadow: 0 6px 32px 0 rgba(76, 75, 162, 0.08);
+    border: 1.5px solid #ece6fa;
+    padding: 32px 32px 24px 32px;
+}
+
+.section-title {
+    display: flex;
+    align-items: center;
+    font-size: 1.35rem;
+    font-weight: 700;
+    color: #4b2996;
+    margin-bottom: 28px;
+    letter-spacing: 0.5px;
+    text-transform: none;
+    background: none;
+    border: none;
+    padding-left: 0;
+    position: relative;
+    padding-bottom: 8px;
+    border-bottom: 2px solid #ecf0f1;
+}
+
+.section-title-spacer {
+    flex: 1 1 auto;
+}
+
+.accent-bar {
+    display: inline-block;
+    width: 7px;
+    height: 28px;
+    border-radius: 4px;
+    background: linear-gradient(180deg, #764ba2 0%, #667eea 100%);
+    margin-right: 16px;
+}
+
+.overview-section, .table-section, .citation-section {
+    margin-bottom: 56px;
+}
+
+.overview-content {
+    font-size: 1.08rem;
+    color: #3a3550;
+    line-height: 1.7;
+    padding-left: 2px;
+    border-left: 4px solid #ece6fa;
+    padding-left: 24px;
+    background: none;
+}
+
+.overview-content p {
+    margin-bottom: 18px;
+    margin-top: 0;
+}
+
+.overview-content h4 {
+    font-size: 1.13rem;
+    font-weight: 700;
+    color: #764ba2;
+    margin-top: 28px;
+    margin-bottom: 10px;
+    letter-spacing: 0.02em;
+}
+
+.overview-content ul,
+.overview-content ol {
+    margin: 0 0 18px 24px;
+    padding-left: 18px;
+}
+
+.overview-content ul li,
+.overview-content ol li {
+    margin-bottom: 8px;
+    line-height: 1.6;
+    font-size: 1.05rem;
+}
+
+.overview-content ul li:last-child,
+.overview-content ol li:last-child {
+    margin-bottom: 0;
+}
+
+.citation-content {
+    font-size: 1.08rem;
+    color: #3a3550;
+    line-height: 1.7;
+    padding-left: 2px;
+}
+
+.citation-content em {
+    color: #764ba2;
+    font-size: 1rem;
+    font-style: italic;
+    background: #f3f0fa;
+    padding: 2px 6px;
+    border-radius: 4px;
+}
+
+.table-container {
+    overflow-x: auto;
+    background: #f8f9fa;
+    border-radius: 12px;
+    padding: 20px;
+    max-height: 480px;
+    overflow-y: auto;
+}
+
+table {
+    width: 100%;
+    border-collapse: collapse;
+    background: white;
+    border-radius: 8px;
+    overflow: hidden;
+    box-shadow: 0 2px 8px rgba(0,0,0,0.1);
+}
+
+th, td {
+    padding: 14px 18px;
+    border-bottom: 1px solid #e9ecef;
+}
+
+th {
+    background: #764ba2;
+    color: white;
+    font-weight: 700;
+    font-size: 1rem;
+    cursor: pointer;
+    transition: background-color 0.3s ease;
+    position: sticky;
+    top: 0;
+    z-index: 2;
+    text-transform: none;
+    letter-spacing: 0.1em;
+    padding-right: 32px;
+}
+
+th:hover {
+    background: #5e388e;
+}
+
+th.sortable::after {
+    content: '';
+    display: inline-block;
+    position: absolute;
+    right: 12px;
+    top: 50%;
+    transform: translateY(-50%);
+    width: 16px;
+    height: 16px;
+    background-repeat: no-repeat;
+    background-position: center;
+    background-size: 16px 16px;
+    opacity: 0.7;
+    /* Default: double chevron (unsorted) */
+    background-image: url('data:image/svg+xml;utf8,<svg width="16" height="16" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M4 6l4-4 4 4" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/><path d="M4 10l4 4 4-4" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/></svg>');
+}
+
+th.sort-asc::after {
+    /* Up chevron */
+    background-image: url('data:image/svg+xml;utf8,<svg width="16" height="16" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M4 10l4-4 4 4" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/></svg>');
+    opacity: 1;
+}
+
+th.sort-desc::after {
+    /* Down chevron */
+    background-image: url('data:image/svg+xml;utf8,<svg width="16" height="16" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M4 6l4 4 4-4" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/></svg>');
+    opacity: 1;
+}
+
+.model-cell, th:first-child {
+    text-align: left;
+}
+
+td:not(.model-cell), th:not(:first-child) {
+    text-align: right;
+}
+
+td {
+    font-size: 1rem;
+    color: #4b2996;
+    font-weight: 500;
+}
+
+tr:hover {
+    background: #f3f0fa;
+}
+
+.score-cell {
+    font-weight: 700;
+    color: #764ba2;
+}
+
+.model-cell {
+    font-weight: 700;
+    color: #495057;
+}
+
+.loading {
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: rgba(0,0,0,0.8);
+    display: flex;
+    flex-direction: column;
+    justify-content: center;
+    align-items: center;
+    z-index: 1000;
+    color: white;
+}
+
+.loading.hidden {
+    display: none;
+}
+
+.spinner {
+    width: 50px;
+    height: 50px;
+    border: 4px solid #f3f3f3;
+    border-top: 4px solid #764ba2;
+    border-radius: 50%;
+    animation: spin 1s linear infinite;
+    margin-bottom: 20px;
+}
+
+@keyframes spin {
+    0% { transform: rotate(0deg); }
+    100% { transform: rotate(360deg); }
+}
+
+.no-data {
+    text-align: center;
+    padding: 40px;
+    color: #6c757d;
+    font-size: 1.1rem;
+}
+
+.no-data i {
+    font-size: 3rem;
+    margin-bottom: 20px;
+    opacity: 0.5;
+}
+
+@media (max-width: 768px) {
+    .container {
+        padding: 10px;
+    }
+    .header h1 {
+        font-size: 2rem;
+    }
+    .dashboard.card {
+        padding: 12px 4px 12px 4px;
+    }
+    .card {
+        padding: 12px 4px 12px 4px;
+    }
+    .table-container {
+        padding: 10px;
+    }
+    th, td {
+        padding: 8px 8px;
+        font-size: 0.92rem;
+    }
+    .overview-section, .table-section, .citation-section {
+        margin-bottom: 36px;
+    }
+}
+
+.judge-section {
+    margin-bottom: 36px;
+}
+
+.judge-toggle {
+    display: flex;
+    gap: 0;
+    border-radius: 10px;
+    overflow: hidden;
+    border: 2px solid #764ba2;
+    width: fit-content;
+}
+
+.judge-btn {
+    padding: 10px 28px;
+    font-size: 1rem;
+    font-weight: 700;
+    font-family: 'Inter', sans-serif;
+    cursor: pointer;
+    border: none;
+    background: white;
+    color: #764ba2;
+    transition: background 0.2s, color 0.2s;
+    letter-spacing: 0.03em;
+}
+
+.judge-btn:not(:last-child) {
+    border-right: 2px solid #764ba2;
+}
+
+.judge-btn:hover {
+    background: #f3eaff;
+}
+
+.judge-btn.active {
+    background: linear-gradient(135deg, #764ba2 0%, #667eea 100%);
+    color: white;
+}
+
+.highlight-row {
+    background: #f3eaff !important;
+    box-shadow: 0 2px 8px 0 rgba(118, 75, 162, 0.08);
+}
+
+.model-link {
+    color: #764ba2;
+    font-weight: 700;
+    text-decoration: none;
+    transition: color 0.2s;
+}
+
+.model-link:hover {
+    color: #4b2996;
+    text-decoration: none;
+}
+
+.external-links {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    margin-top: 1.2rem;
+    margin-bottom: 0.5rem;
+    gap: 1.5rem;
+}
+
+.external-link {
+    display: flex;
+    align-items: center;
+    color: #764ba2;
+    text-decoration: none;
+    font-weight: 700;
+    transition: color 0.2s, transform 0.2s;
+}
+
+.external-link svg {
+    width: 2.1rem;
+    height: 2.1rem;
+    display: block;
+}
+
+.external-link:hover {
+    color: #4b2996;
+    transform: scale(1.08);
+}
+
+.external-links-text {
+    display: flex;
+    justify-content: flex-end;
+    align-items: center;
+    margin: 0;
+    font-size: 1.05rem;
+    font-weight: 700;
+    gap: 0.5rem;
+    width: auto;
+}
+
+.external-link-text {
+    color: #4b2996;
+    background: none;
+    text-decoration: none;
+    font-weight: 700;
+    letter-spacing: 0.01em;
+    padding: 0.18em 0.7em;
+    border-radius: 18px;
+    transition: color 0.2s, background 0.2s, box-shadow 0.2s;
+    box-shadow: none;
+    display: inline-block;
+}
+
+.external-link-text:hover {
+    color: #fff;
+    background: linear-gradient(90deg, #764ba2 60%, #667eea 100%);
+    text-decoration: none;
+    box-shadow: 0 2px 8px 0 rgba(118, 75, 162, 0.13);
+}
+
+.divider {
+    display: inline-block;
+    color: #bba6d6;
+    font-size: 1.1em;
+    font-weight: 400;
+    margin: 0 0.0em;
+    user-select: none;
+    vertical-align: middle;
+    line-height: 0.5;
+    letter-spacing: 0;
+}