Spaces:
Running
Running
| { | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "Qwen3-235B-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 | |
| }, | |
| "Qwen3-30B-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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "Qwen3-32B-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 | |
| }, | |
| "Qwen3-8B": { | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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-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-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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "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 | |
| }, | |
| "gpt-4.1-2025-04-14": { | |
| "comprehension_score": 5.0, | |
| "structure_score": 5.0, | |
| "prose_style_score": 5.0, | |
| "creativity_score": 5.0, | |
| "depth_score": 5.0, | |
| "helpfulness_score": 5.0, | |
| "overall_score": 5.0 | |
| } | |
| } |