{
  "id": "model_comparison",
  "label": "Model Comparison",
  "snapshot_date": "2026-06-06",
  "evidence_summary": {
    "surface": "model_comparison",
    "claim_state": "directional_model_comparison",
    "model_comparison_claim_state": "directional_model_comparison",
    "model_comparison_order_state": "directional_order_supported",
    "model_comparison_basis": "all_core_items_directional",
    "strict_rank_order_claim_state": "not_claimed_directional_order",
    "strict_rank_order_supported": false,
    "rank_discriminating_subset_state": "not_primary_contract",
    "directional_model_count": 8,
    "mission_evidence_state": "model_behavior_evidence",
    "directional_gaps": {
      "gemini_3_5_flash": {
        "directional_model_comparison_score": 45,
        "composite_score_directional": 45,
        "gap_to_best_directional": -8.9,
        "gap_to_median_directional": -0.15,
        "directional_rank": 5
      },
      "claude_opus_4_8": {
        "directional_model_comparison_score": 43,
        "composite_score_directional": 43,
        "gap_to_best_directional": -10.9,
        "gap_to_median_directional": -2.15,
        "directional_rank": 8
      },
      "claude_sonnet_4_6": {
        "directional_model_comparison_score": 43.4,
        "composite_score_directional": 43.4,
        "gap_to_best_directional": -10.5,
        "gap_to_median_directional": -1.75,
        "directional_rank": 7
      },
      "gpt_5_5": {
        "directional_model_comparison_score": 45.4,
        "composite_score_directional": 45.4,
        "gap_to_best_directional": -8.5,
        "gap_to_median_directional": 0.25,
        "directional_rank": 3
      },
      "grok_4_3": {
        "directional_model_comparison_score": 45.5,
        "composite_score_directional": 45.5,
        "gap_to_best_directional": -8.4,
        "gap_to_median_directional": 0.35,
        "directional_rank": 2
      },
      "deepseek_v4_flash": {
        "directional_model_comparison_score": 53.9,
        "composite_score_directional": 53.9,
        "gap_to_best_directional": 0,
        "gap_to_median_directional": 8.75,
        "directional_rank": 1
      },
      "deepseek_v4_pro": {
        "directional_model_comparison_score": 45.3,
        "composite_score_directional": 45.3,
        "gap_to_best_directional": -8.6,
        "gap_to_median_directional": 0.15,
        "directional_rank": 4
      },
      "kimi_k2_6": {
        "directional_model_comparison_score": 43.5,
        "composite_score_directional": 43.5,
        "gap_to_best_directional": -10.4,
        "gap_to_median_directional": -1.65,
        "directional_rank": 6
      }
    },
    "directional_gaps_by_metric_family": {
      "allfaith_source_match": {
        "gemini_3_5_flash": {
          "directional_score": 99.8,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 5.2,
          "directional_rank": 1
        },
        "claude_opus_4_8": {
          "directional_score": 94.7,
          "gap_to_best_directional": -5.1,
          "gap_to_median_directional": 0.1,
          "directional_rank": 4
        },
        "claude_sonnet_4_6": {
          "directional_score": 94.5,
          "gap_to_best_directional": -5.3,
          "gap_to_median_directional": -0.1,
          "directional_rank": 5
        },
        "gpt_5_5": {
          "directional_score": 96.5,
          "gap_to_best_directional": -3.3,
          "gap_to_median_directional": 1.9,
          "directional_rank": 2
        },
        "grok_4_3": {
          "directional_score": 93.6,
          "gap_to_best_directional": -6.2,
          "gap_to_median_directional": -1,
          "directional_rank": 6
        },
        "deepseek_v4_flash": {
          "directional_score": 93,
          "gap_to_best_directional": -6.8,
          "gap_to_median_directional": -1.6,
          "directional_rank": 7
        },
        "deepseek_v4_pro": {
          "directional_score": 94.9,
          "gap_to_best_directional": -4.9,
          "gap_to_median_directional": 0.3,
          "directional_rank": 3
        },
        "kimi_k2_6": {
          "directional_score": 88.6,
          "gap_to_best_directional": -11.2,
          "gap_to_median_directional": -6,
          "directional_rank": 8
        }
      },
      "bounded_faith_handling": {
        "gemini_3_5_flash": {
          "directional_score": 99.9,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 2.1,
          "directional_rank": 1
        },
        "claude_opus_4_8": {
          "directional_score": 98.8,
          "gap_to_best_directional": -1.1,
          "gap_to_median_directional": 1,
          "directional_rank": 2
        },
        "claude_sonnet_4_6": {
          "directional_score": 98.4,
          "gap_to_best_directional": -1.5,
          "gap_to_median_directional": 0.6,
          "directional_rank": 4
        },
        "gpt_5_5": {
          "directional_score": 98.7,
          "gap_to_best_directional": -1.2,
          "gap_to_median_directional": 0.9,
          "directional_rank": 3
        },
        "grok_4_3": {
          "directional_score": 97,
          "gap_to_best_directional": -2.9,
          "gap_to_median_directional": -0.8,
          "directional_rank": 6
        },
        "deepseek_v4_flash": {
          "directional_score": 95.3,
          "gap_to_best_directional": -4.6,
          "gap_to_median_directional": -2.5,
          "directional_rank": 8
        },
        "deepseek_v4_pro": {
          "directional_score": 97.2,
          "gap_to_best_directional": -2.7,
          "gap_to_median_directional": -0.6,
          "directional_rank": 5
        },
        "kimi_k2_6": {
          "directional_score": 96.6,
          "gap_to_best_directional": -3.3,
          "gap_to_median_directional": -1.2,
          "directional_rank": 7
        }
      },
      "faith_inclusive_vs_secular_only": {
        "gemini_3_5_flash": {
          "directional_score": 90.1,
          "gap_to_best_directional": -0.4,
          "gap_to_median_directional": 1.5,
          "directional_rank": 2
        },
        "claude_opus_4_8": {
          "directional_score": 88.3,
          "gap_to_best_directional": -2.2,
          "gap_to_median_directional": -0.3,
          "directional_rank": 5
        },
        "claude_sonnet_4_6": {
          "directional_score": 88.9,
          "gap_to_best_directional": -1.6,
          "gap_to_median_directional": 0.3,
          "directional_rank": 4
        },
        "gpt_5_5": {
          "directional_score": 88.2,
          "gap_to_best_directional": -2.3,
          "gap_to_median_directional": -0.4,
          "directional_rank": 6
        },
        "grok_4_3": {
          "directional_score": 89.3,
          "gap_to_best_directional": -1.2,
          "gap_to_median_directional": 0.7,
          "directional_rank": 3
        },
        "deepseek_v4_flash": {
          "directional_score": 87.6,
          "gap_to_best_directional": -2.9,
          "gap_to_median_directional": -1,
          "directional_rank": 7
        },
        "deepseek_v4_pro": {
          "directional_score": 90.5,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 1.9,
          "directional_rank": 1
        },
        "kimi_k2_6": {
          "directional_score": 83.1,
          "gap_to_best_directional": -7.4,
          "gap_to_median_directional": -5.5,
          "directional_rank": 8
        }
      },
      "human_reference_divergence": {
        "gemini_3_5_flash": {
          "directional_score": 2.5,
          "gap_to_best_directional": -35,
          "gap_to_median_directional": -22.55,
          "directional_rank": 8
        },
        "claude_opus_4_8": {
          "directional_score": 25.1,
          "gap_to_best_directional": -12.4,
          "gap_to_median_directional": 0.05,
          "directional_rank": 4
        },
        "claude_sonnet_4_6": {
          "directional_score": 25,
          "gap_to_best_directional": -12.5,
          "gap_to_median_directional": -0.05,
          "directional_rank": 5
        },
        "gpt_5_5": {
          "directional_score": 9,
          "gap_to_best_directional": -28.5,
          "gap_to_median_directional": -16.05,
          "directional_rank": 7
        },
        "grok_4_3": {
          "directional_score": 37.5,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 12.45,
          "directional_rank": 1
        },
        "deepseek_v4_flash": {
          "directional_score": 35.3,
          "gap_to_best_directional": -2.2,
          "gap_to_median_directional": 10.25,
          "directional_rank": 2
        },
        "deepseek_v4_pro": {
          "directional_score": 29.1,
          "gap_to_best_directional": -8.4,
          "gap_to_median_directional": 4.05,
          "directional_rank": 3
        },
        "kimi_k2_6": {
          "directional_score": 22.4,
          "gap_to_best_directional": -15.1,
          "gap_to_median_directional": -2.65,
          "directional_rank": 6
        }
      },
      "secular_default_omission": {
        "gemini_3_5_flash": {
          "directional_score": 100,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 0.05,
          "directional_rank": 3
        },
        "claude_opus_4_8": {
          "directional_score": 100,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 0.05,
          "directional_rank": 1
        },
        "claude_sonnet_4_6": {
          "directional_score": 100,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 0.05,
          "directional_rank": 2
        },
        "gpt_5_5": {
          "directional_score": 100,
          "gap_to_best_directional": 0,
          "gap_to_median_directional": 0.05,
          "directional_rank": 4
        },
        "grok_4_3": {
          "directional_score": 98.2,
          "gap_to_best_directional": -1.8,
          "gap_to_median_directional": -1.75,
          "directional_rank": 7
        },
        "deepseek_v4_flash": {
          "directional_score": 94.4,
          "gap_to_best_directional": -5.6,
          "gap_to_median_directional": -5.55,
          "directional_rank": 8
        },
        "deepseek_v4_pro": {
          "directional_score": 98.2,
          "gap_to_best_directional": -1.8,
          "gap_to_median_directional": -1.75,
          "directional_rank": 6
        },
        "kimi_k2_6": {
          "directional_score": 99.9,
          "gap_to_best_directional": -0.1,
          "gap_to_median_directional": -0.05,
          "directional_rank": 5
        }
      }
    },
    "strict_rank_order": {
      "strict_rank_order_claim_state": "not_claimed_directional_order",
      "strict_rank_order_supported": false,
      "strict_rank_order_item_state_counts": {
        "strict_rank_order_not_claimed": 8
      },
      "rankable_model_count": 0
    },
    "rank_discriminating_subset": {
      "rank_discriminating_subset_state": "not_primary_contract",
      "included_models": [],
      "excluded_models": [
        "claude_opus_4_8",
        "claude_sonnet_4_6",
        "deepseek_v4_flash",
        "deepseek_v4_pro",
        "gemini_3_5_flash",
        "gpt_5_5",
        "grok_4_3",
        "kimi_k2_6"
      ],
      "included_model_count": 0,
      "excluded_model_count": 8,
      "minimum_included_models": 2,
      "strict_rank_order_claim_state": "not_claimed_directional_order",
      "strict_rank_order_supported": false
    },
    "margin_of_error": 0.9,
    "uncertainty_state": "uncertainty_available",
    "source_alignment_state": "matches_displayed_score",
    "uncertainty_summary": {
      "model_count": 8,
      "rankable_model_count": 0,
      "directional_model_count": 8,
      "uncertainty_state_counts": {
        "uncertainty_available": 8
      },
      "source_alignment_state_counts": {
        "matches_displayed_score": 8
      },
      "margin_of_error": 0.9,
      "margin_of_error_by_model": {
        "claude_opus_4_8": 0.3,
        "claude_sonnet_4_6": 0.3,
        "deepseek_v4_flash": 0.9,
        "deepseek_v4_pro": 0.6,
        "gemini_3_5_flash": 0.4,
        "gpt_5_5": 0.5,
        "grok_4_3": 0.7,
        "kimi_k2_6": 0.4
      },
      "uncertainty_state": "uncertainty_available",
      "source_alignment_state": "matches_displayed_score"
    },
    "reason_codes": [
      "model_comparison_score_source_directional"
    ],
    "degraded_reason_codes": []
  },
  "links": {
    "index": "https://fri.faithandmedia.dev/api/v1/index.json",
    "report_html": "https://fri.faithandmedia.dev/core/#model-comparison",
    "report_access": "authenticated"
  }
}
