{
    "data": {
        "run_id": 411,
        "run_date": "2026-11-04",
        "benchmark_version": "v7",
        "rankings": [
            {
                "model_slug": "gpt-6-astra",
                "model_name": "GPT-6 Astra",
                "dcd_raw": 90.5,
                "rank": 1,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 82.44,
                "main_rank": 2,
                "rank_diff_vs_main": 1
            },
            {
                "model_slug": "gemini-3.1-pro",
                "model_name": "Gemini 3.1 Pro",
                "dcd_raw": 89.97,
                "rank": 2,
                "dcd_r1_score": 1,
                "dcd_r2_score": 0,
                "dcd_r3_score": 1,
                "core_overall_display": 61.56,
                "main_rank": 12,
                "rank_diff_vs_main": 10
            },
            {
                "model_slug": "glm-4.6",
                "model_name": "GLM-4.6",
                "dcd_raw": 89.97,
                "rank": 3,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 34.39,
                "main_rank": 14,
                "rank_diff_vs_main": 11
            },
            {
                "model_slug": "claude-opus-4.7",
                "model_name": "Claude Opus 4.7",
                "dcd_raw": 89.3,
                "rank": 4,
                "dcd_r1_score": 1,
                "dcd_r2_score": 0,
                "dcd_r3_score": 2,
                "core_overall_display": 82.53,
                "main_rank": 1,
                "rank_diff_vs_main": -3
            },
            {
                "model_slug": "gpt-6-sol",
                "model_name": "GPT-6 Sol",
                "dcd_raw": 89.3,
                "rank": 5,
                "dcd_r1_score": 1,
                "dcd_r2_score": 0,
                "dcd_r3_score": 2,
                "core_overall_display": 76.86,
                "main_rank": 8,
                "rank_diff_vs_main": 3
            },
            {
                "model_slug": "claude-sonnet-4.6",
                "model_name": "Claude Sonnet 4.6",
                "dcd_raw": 88.9,
                "rank": 6,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 78.07,
                "main_rank": 7,
                "rank_diff_vs_main": 1
            },
            {
                "model_slug": "grok-4",
                "model_name": "Grok 4",
                "dcd_raw": 88.27,
                "rank": 7,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 79.05,
                "main_rank": 5,
                "rank_diff_vs_main": -2
            },
            {
                "model_slug": "gpt-o3",
                "model_name": "GPT-o3",
                "dcd_raw": 86.93,
                "rank": 8,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 75.39,
                "main_rank": 9,
                "rank_diff_vs_main": 1
            },
            {
                "model_slug": "gpt-6-luna",
                "model_name": "GPT-6 Luna",
                "dcd_raw": 85.77,
                "rank": 9,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 78.87,
                "main_rank": 6,
                "rank_diff_vs_main": -3
            },
            {
                "model_slug": "gpt-5.5",
                "model_name": "GPT-5.5",
                "dcd_raw": 81.27,
                "rank": 10,
                "dcd_r1_score": 1,
                "dcd_r2_score": 0,
                "dcd_r3_score": 1,
                "core_overall_display": 74.22,
                "main_rank": 10,
                "rank_diff_vs_main": 0
            },
            {
                "model_slug": "deepseek-v4-pro",
                "model_name": "DeepSeek V4 Pro",
                "dcd_raw": 78.57,
                "rank": 11,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 73.67,
                "main_rank": 11,
                "rank_diff_vs_main": 0
            },
            {
                "model_slug": "gemini-2.5-pro",
                "model_name": "Gemini 2.5 Pro",
                "dcd_raw": 77.23,
                "rank": 12,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 51.43,
                "main_rank": 13,
                "rank_diff_vs_main": 1
            },
            {
                "model_slug": "gpt-6.1-sol",
                "model_name": "GPT-6.1 Sol",
                "dcd_raw": 77.2,
                "rank": 13,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 79.29,
                "main_rank": 4,
                "rank_diff_vs_main": -9
            },
            {
                "model_slug": "qwen3-max",
                "model_name": "Qwen3 Max",
                "dcd_raw": 76.5,
                "rank": 14,
                "dcd_r1_score": 0,
                "dcd_r2_score": 0,
                "dcd_r3_score": 0,
                "core_overall_display": 0,
                "main_rank": 15,
                "rank_diff_vs_main": 1
            },
            {
                "model_slug": "doubao-pro",
                "model_name": "豆包 Pro",
                "dcd_raw": 58.7,
                "rank": 15,
                "dcd_r1_score": 1,
                "dcd_r2_score": 1,
                "dcd_r3_score": 2,
                "core_overall_display": 79.57,
                "main_rank": 3,
                "rank_diff_vs_main": -12
            }
        ]
    },
    "meta": {
        "experimental": true,
        "experimental_note": "WDCD is an experimental dimension introduced in v7. Data is being collected and stabilized. Not yet counted in main leaderboard.",
        "experimental_since": "2026-05-01",
        "stability_assessment_date": "2026-08-01",
        "total_questions": 30,
        "total_models": 15,
        "subtypes": [
            "data_boundary",
            "resource_limit",
            "business_rule",
            "security",
            "engineering"
        ]
    }
}