{
  "schema_version": 2,
  "title": "RISE Leaderboard",
  "benchmarks": [
    {
      "id": "risebench-plusplus",
      "name": "RISEBench++",
      "case_count": 1000,
      "available_result_languages": [
        "en",
        "zh"
      ],
      "accuracy_unit": "%",
      "metric_unit": "/100",
      "score_decimals": 1,
      "default_sort": "total",
      "dimensions": [
        {
          "key": "temporal",
          "label": "Temporal",
          "description": "Infer how a scene changes over time."
        },
        {
          "key": "causal",
          "label": "Causal",
          "description": "Reason about causes, actions, and their consequences."
        },
        {
          "key": "spatial",
          "label": "Spatial",
          "description": "Reason about spatial relationships and transformations."
        },
        {
          "key": "logical",
          "label": "Logical",
          "description": "Apply explicit rules, patterns, and logical constraints."
        },
        {
          "key": "counterfactual",
          "label": "Counterfactual",
          "description": "Visualize outcomes under hypothetical or contrary-to-fact conditions."
        },
        {
          "key": "hybrid",
          "label": "Hybrid",
          "description": "Combine reasoning across three to five successive editing instructions."
        }
      ],
      "metrics": [
        {
          "key": "instruction_reasoning",
          "label": "Instruction Reasoning",
          "description": "Whether the edit realizes the intended reasoning outcome."
        },
        {
          "key": "appearance_consistency",
          "label": "Appearance Consistency",
          "description": "Whether content that should remain unchanged is preserved."
        },
        {
          "key": "visual_plausibility",
          "label": "Visual Plausibility",
          "description": "Visual quality and plausibility; logical tasks are excluded."
        }
      ],
      "accuracy_columns": [
        {
          "key": "temporal",
          "label": "Temporal",
          "description": "Infer how a scene changes over time."
        },
        {
          "key": "causal",
          "label": "Causal",
          "description": "Reason about causes, actions, and their consequences."
        },
        {
          "key": "spatial",
          "label": "Spatial",
          "description": "Reason about spatial relationships and transformations."
        },
        {
          "key": "logical",
          "label": "Logical",
          "description": "Apply explicit rules, patterns, and logical constraints."
        },
        {
          "key": "counterfactual",
          "label": "Counterfactual",
          "description": "Visualize outcomes under hypothetical or contrary-to-fact conditions."
        },
        {
          "key": "hybrid",
          "label": "Hybrid",
          "description": "Combine reasoning across three to five successive editing instructions."
        },
        {
          "key": "single",
          "label": "Single",
          "description": "Accuracy on single-image cases."
        },
        {
          "key": "multi",
          "label": "Multi",
          "description": "Accuracy on multi-image cases. Not evaluated for models without multi-image support."
        },
        {
          "key": "total",
          "label": "Total",
          "description": "Accuracy on the complete benchmark. Not evaluated for single-image-only models."
        }
      ],
      "links": {
        "paper": "https://arxiv.org/abs/2610.12343",
        "data": "https://huggingface.co/datasets/VisionXLab/RISEBench-plusplus",
        "outputs": "https://huggingface.co/datasets/VisionXLab/RISEBench-plusplus_Outputs",
        "github": "https://github.com/VisionXLab/RISEBench/tree/main/RISEBench%2B%2B"
      },
      "judges": {
        "instruction_reasoning": "Gemini-3-Flash",
        "appearance_consistency": "Gemini-3-Flash",
        "visual_plausibility": "Gemini-3.1-Flash-Lite"
      },
      "results_by_language": {
        "en": {
          "language": "English",
          "language_code": "en",
          "model_count": 58,
          "groups": [
            {
              "id": "closed",
              "label": "Closed-source Models",
              "count": 19
            },
            {
              "id": "open",
              "label": "Open-source Models",
              "count": 34
            },
            {
              "id": "agentic",
              "label": "Agentic Methods",
              "count": 5
            }
          ],
          "models": [
            {
              "id": "gpt-image-2-5-sunburst",
              "name": "GPT-Image-2.5 Sunburst",
              "group": "closed",
              "multi_image": true,
              "source_order": 1,
              "accuracy": {
                "temporal": 67.5,
                "causal": 69.0,
                "spatial": 64.0,
                "logical": 27.0,
                "counterfactual": 72.0,
                "hybrid": 39.0,
                "single": 56.9,
                "multi": 52.6,
                "total": 56.6
              },
              "metrics": {
                "instruction_reasoning": 68.1,
                "appearance_consistency": 96.3,
                "visual_plausibility": 98.0
              }
            },
            {
              "id": "nano-banana-pro",
              "name": "Nano Banana Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 2,
              "accuracy": {
                "temporal": 63.0,
                "causal": 71.0,
                "spatial": 51.5,
                "logical": 36.0,
                "counterfactual": 65.0,
                "hybrid": 38.0,
                "single": 55.4,
                "multi": 44.9,
                "total": 54.6
              },
              "metrics": {
                "instruction_reasoning": 69.8,
                "appearance_consistency": 87.7,
                "visual_plausibility": 96.8
              }
            },
            {
              "id": "nano-banana-2",
              "name": "Nano Banana 2",
              "group": "closed",
              "multi_image": true,
              "source_order": 3,
              "accuracy": {
                "temporal": 67.5,
                "causal": 67.0,
                "spatial": 45.0,
                "logical": 28.5,
                "counterfactual": 62.0,
                "hybrid": 30.0,
                "single": 51.3,
                "multi": 44.9,
                "total": 50.8
              },
              "metrics": {
                "instruction_reasoning": 68.5,
                "appearance_consistency": 91.1,
                "visual_plausibility": 97.2
              }
            },
            {
              "id": "gpt-image-2",
              "name": "GPT-Image-2",
              "group": "closed",
              "multi_image": true,
              "source_order": 4,
              "accuracy": {
                "temporal": 59.5,
                "causal": 64.5,
                "spatial": 60.5,
                "logical": 15.0,
                "counterfactual": 58.0,
                "hybrid": 21.0,
                "single": 48.2,
                "multi": 43.6,
                "total": 47.8
              },
              "metrics": {
                "instruction_reasoning": 61.5,
                "appearance_consistency": 95.2,
                "visual_plausibility": 97.6
              }
            },
            {
              "id": "gpt-image-2-5-flare",
              "name": "GPT-Image-2.5 Flare",
              "group": "closed",
              "multi_image": true,
              "source_order": 5,
              "accuracy": {
                "temporal": 61.0,
                "causal": 63.0,
                "spatial": 56.5,
                "logical": 11.0,
                "counterfactual": 57.0,
                "hybrid": 20.0,
                "single": 46.6,
                "multi": 38.5,
                "total": 46.0
              },
              "metrics": {
                "instruction_reasoning": 59.8,
                "appearance_consistency": 93.2,
                "visual_plausibility": 98.3
              }
            },
            {
              "id": "luma-uni-1",
              "name": "Luma Uni-1",
              "group": "closed",
              "multi_image": true,
              "source_order": 6,
              "accuracy": {
                "temporal": 61.0,
                "causal": 57.0,
                "spatial": 50.5,
                "logical": 18.0,
                "counterfactual": 55.0,
                "hybrid": 24.0,
                "single": 45.7,
                "multi": 39.7,
                "total": 45.2
              },
              "metrics": {
                "instruction_reasoning": 62.2,
                "appearance_consistency": 91.0,
                "visual_plausibility": 94.7
              }
            },
            {
              "id": "qwen-image-3-0",
              "name": "Qwen-Image-3.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 7,
              "accuracy": {
                "temporal": 58.5,
                "causal": 47.5,
                "spatial": 41.0,
                "logical": 36.0,
                "counterfactual": 49.0,
                "hybrid": 34.0,
                "single": 44.5,
                "multi": 50.0,
                "total": 44.9
              },
              "metrics": {
                "instruction_reasoning": 68.4,
                "appearance_consistency": 87.3,
                "visual_plausibility": 95.9
              }
            },
            {
              "id": "nano-banana-2-lite",
              "name": "Nano Banana 2 Lite",
              "group": "closed",
              "multi_image": true,
              "source_order": 8,
              "accuracy": {
                "temporal": 60.5,
                "causal": 61.5,
                "spatial": 46.5,
                "logical": 15.0,
                "counterfactual": 62.0,
                "hybrid": 12.0,
                "single": 44.5,
                "multi": 39.7,
                "total": 44.1
              },
              "metrics": {
                "instruction_reasoning": 60.8,
                "appearance_consistency": 89.7,
                "visual_plausibility": 96.3
              }
            },
            {
              "id": "flux-2-max",
              "name": "FLUX.2 Max",
              "group": "closed",
              "multi_image": true,
              "source_order": 9,
              "accuracy": {
                "temporal": 57.0,
                "causal": 57.0,
                "spatial": 42.5,
                "logical": 12.5,
                "counterfactual": 61.0,
                "hybrid": 18.0,
                "single": 41.5,
                "multi": 43.6,
                "total": 41.7
              },
              "metrics": {
                "instruction_reasoning": 61.5,
                "appearance_consistency": 79.2,
                "visual_plausibility": 95.5
              }
            },
            {
              "id": "gpt-image-1-5",
              "name": "GPT-Image-1.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 10,
              "accuracy": {
                "temporal": 57.5,
                "causal": 62.5,
                "spatial": 39.5,
                "logical": 8.0,
                "counterfactual": 59.0,
                "hybrid": 12.0,
                "single": 41.2,
                "multi": 33.3,
                "total": 40.6
              },
              "metrics": {
                "instruction_reasoning": 59.9,
                "appearance_consistency": 81.0,
                "visual_plausibility": 96.5
              }
            },
            {
              "id": "flux-2-pro",
              "name": "FLUX.2 Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 11,
              "accuracy": {
                "temporal": 53.5,
                "causal": 48.5,
                "spatial": 36.5,
                "logical": 10.5,
                "counterfactual": 61.0,
                "hybrid": 18.0,
                "single": 37.3,
                "multi": 42.3,
                "total": 37.7
              },
              "metrics": {
                "instruction_reasoning": 57.5,
                "appearance_consistency": 74.7,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "nano-banana",
              "name": "Nano Banana",
              "group": "closed",
              "multi_image": true,
              "source_order": 12,
              "accuracy": {
                "temporal": 52.0,
                "causal": 52.5,
                "spatial": 39.5,
                "logical": 11.0,
                "counterfactual": 47.0,
                "hybrid": 11.0,
                "single": 36.8,
                "multi": 37.2,
                "total": 36.8
              },
              "metrics": {
                "instruction_reasoning": 52.9,
                "appearance_consistency": 84.1,
                "visual_plausibility": 95.8
              }
            },
            {
              "id": "hunyuanimage-3-5",
              "name": "HunyuanImage-3.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 13,
              "accuracy": {
                "temporal": 43.5,
                "causal": 46.0,
                "spatial": 43.5,
                "logical": 14.0,
                "counterfactual": 37.0,
                "hybrid": 17.0,
                "single": 34.5,
                "multi": 38.5,
                "total": 34.8
              },
              "metrics": {
                "instruction_reasoning": 51.3,
                "appearance_consistency": 93.4,
                "visual_plausibility": 95.2
              }
            },
            {
              "id": "wan2-7-image-pro",
              "name": "Wan2.7-Image-Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 14,
              "accuracy": {
                "temporal": 41.5,
                "causal": 52.0,
                "spatial": 32.5,
                "logical": 10.5,
                "counterfactual": 49.0,
                "hybrid": 13.0,
                "single": 36.3,
                "multi": 0.0,
                "total": 33.5
              },
              "metrics": {
                "instruction_reasoning": 48.8,
                "appearance_consistency": 80.1,
                "visual_plausibility": 93.3
              }
            },
            {
              "id": "gpt-image-1",
              "name": "GPT-Image-1",
              "group": "closed",
              "multi_image": true,
              "source_order": 15,
              "accuracy": {
                "temporal": 51.0,
                "causal": 49.0,
                "spatial": 29.5,
                "logical": 5.5,
                "counterfactual": 41.0,
                "hybrid": 7.0,
                "single": 32.3,
                "multi": 25.6,
                "total": 31.8
              },
              "metrics": {
                "instruction_reasoning": 53.4,
                "appearance_consistency": 73.6,
                "visual_plausibility": 95.6
              }
            },
            {
              "id": "qwen-image-2-0",
              "name": "Qwen-Image-2.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 16,
              "accuracy": {
                "temporal": 44.0,
                "causal": 47.0,
                "spatial": 36.0,
                "logical": 6.5,
                "counterfactual": 36.0,
                "hybrid": 0.0,
                "single": 30.2,
                "multi": 32.1,
                "total": 30.3
              },
              "metrics": {
                "instruction_reasoning": 49.6,
                "appearance_consistency": 79.7,
                "visual_plausibility": 91.5
              }
            },
            {
              "id": "seedream-4-5",
              "name": "Seedream 4.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 17,
              "accuracy": {
                "temporal": 42.5,
                "causal": 42.0,
                "spatial": 26.5,
                "logical": 7.5,
                "counterfactual": 36.0,
                "hybrid": 6.0,
                "single": 28.0,
                "multi": 26.9,
                "total": 27.9
              },
              "metrics": {
                "instruction_reasoning": 49.8,
                "appearance_consistency": 76.0,
                "visual_plausibility": 94.5
              }
            },
            {
              "id": "seedream-5-0",
              "name": "Seedream 5.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 18,
              "accuracy": {
                "temporal": 42.5,
                "causal": 43.0,
                "spatial": 26.0,
                "logical": 5.5,
                "counterfactual": 30.0,
                "hybrid": 3.0,
                "single": 27.2,
                "multi": 20.5,
                "total": 26.7
              },
              "metrics": {
                "instruction_reasoning": 47.8,
                "appearance_consistency": 71.7,
                "visual_plausibility": 94.3
              }
            },
            {
              "id": "step-image-edit-2",
              "name": "Step Image Edit 2",
              "group": "closed",
              "multi_image": false,
              "source_order": 19,
              "accuracy": {
                "temporal": 18.5,
                "causal": 22.9,
                "spatial": 26.4,
                "logical": 1.7,
                "counterfactual": 10.0,
                "hybrid": 1.0,
                "single": 14.9,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 31.0,
                "appearance_consistency": 68.3,
                "visual_plausibility": 86.3
              }
            },
            {
              "id": "hunyuanimage-3-0-instruct",
              "name": "HunyuanImage-3.0-Instruct",
              "group": "open",
              "multi_image": true,
              "source_order": 20,
              "accuracy": {
                "temporal": 30.5,
                "causal": 37.5,
                "spatial": 29.5,
                "logical": 7.0,
                "counterfactual": 21.0,
                "hybrid": 0.0,
                "single": 22.5,
                "multi": 29.5,
                "total": 23.0
              },
              "metrics": {
                "instruction_reasoning": 38.2,
                "appearance_consistency": 75.8,
                "visual_plausibility": 88.5
              }
            },
            {
              "id": "qwen-image-edit-2511",
              "name": "Qwen-Image-Edit-2511",
              "group": "open",
              "multi_image": true,
              "source_order": 21,
              "accuracy": {
                "temporal": 22.0,
                "causal": 24.5,
                "spatial": 23.5,
                "logical": 4.5,
                "counterfactual": 17.0,
                "hybrid": 5.0,
                "single": 16.9,
                "multi": 19.2,
                "total": 17.1
              },
              "metrics": {
                "instruction_reasoning": 36.0,
                "appearance_consistency": 64.0,
                "visual_plausibility": 90.7
              }
            },
            {
              "id": "qwen-image-2-1",
              "name": "Qwen-Image-2.1",
              "group": "open",
              "multi_image": true,
              "source_order": 22,
              "accuracy": {
                "temporal": 21.5,
                "causal": 25.5,
                "spatial": 24.5,
                "logical": 2.0,
                "counterfactual": 16.0,
                "hybrid": 0.0,
                "single": 15.0,
                "multi": 32.1,
                "total": 16.3
              },
              "metrics": {
                "instruction_reasoning": 31.6,
                "appearance_consistency": 77.6,
                "visual_plausibility": 86.2
              }
            },
            {
              "id": "firered-image-edit-1-0",
              "name": "FireRed-Image-Edit-1.0",
              "group": "open",
              "multi_image": true,
              "source_order": 23,
              "accuracy": {
                "temporal": 22.0,
                "causal": 18.0,
                "spatial": 28.0,
                "logical": 2.0,
                "counterfactual": 21.0,
                "hybrid": 2.0,
                "single": 16.1,
                "multi": 19.2,
                "total": 16.3
              },
              "metrics": {
                "instruction_reasoning": 32.2,
                "appearance_consistency": 64.0,
                "visual_plausibility": 93.7
              }
            },
            {
              "id": "firered-image-edit-1-1",
              "name": "FireRed-Image-Edit-1.1",
              "group": "open",
              "multi_image": true,
              "source_order": 24,
              "accuracy": {
                "temporal": 22.5,
                "causal": 23.5,
                "spatial": 22.5,
                "logical": 1.5,
                "counterfactual": 16.0,
                "hybrid": 2.0,
                "single": 14.8,
                "multi": 28.2,
                "total": 15.8
              },
              "metrics": {
                "instruction_reasoning": 32.8,
                "appearance_consistency": 66.2,
                "visual_plausibility": 93.0
              }
            },
            {
              "id": "qwen-image-edit-2509",
              "name": "Qwen-Image-Edit-2509",
              "group": "open",
              "multi_image": true,
              "source_order": 25,
              "accuracy": {
                "temporal": 21.0,
                "causal": 24.5,
                "spatial": 20.0,
                "logical": 0.5,
                "counterfactual": 16.0,
                "hybrid": 0.0,
                "single": 15.0,
                "multi": 12.8,
                "total": 14.8
              },
              "metrics": {
                "instruction_reasoning": 29.8,
                "appearance_consistency": 61.3,
                "visual_plausibility": 85.7
              }
            },
            {
              "id": "hidream-o1-image",
              "name": "HiDream-O1-Image",
              "group": "open",
              "multi_image": true,
              "source_order": 26,
              "accuracy": {
                "temporal": 27.5,
                "causal": 18.0,
                "spatial": 20.5,
                "logical": 3.0,
                "counterfactual": 5.0,
                "hybrid": 0.0,
                "single": 13.6,
                "multi": 23.1,
                "total": 14.3
              },
              "metrics": {
                "instruction_reasoning": 35.2,
                "appearance_consistency": 57.3,
                "visual_plausibility": 87.3
              }
            },
            {
              "id": "flux-2-dev",
              "name": "FLUX.2 Dev",
              "group": "open",
              "multi_image": true,
              "source_order": 27,
              "accuracy": {
                "temporal": 19.5,
                "causal": 27.5,
                "spatial": 17.0,
                "logical": 1.0,
                "counterfactual": 10.0,
                "hybrid": 1.0,
                "single": 12.8,
                "multi": 29.5,
                "total": 14.1
              },
              "metrics": {
                "instruction_reasoning": 31.1,
                "appearance_consistency": 57.7,
                "visual_plausibility": 91.9
              }
            },
            {
              "id": "flux-2-klein-9b",
              "name": "FLUX.2 Klein 9B",
              "group": "open",
              "multi_image": true,
              "source_order": 28,
              "accuracy": {
                "temporal": 16.0,
                "causal": 16.5,
                "spatial": 22.0,
                "logical": 0.5,
                "counterfactual": 17.0,
                "hybrid": 2.0,
                "single": 11.4,
                "multi": 30.8,
                "total": 12.9
              },
              "metrics": {
                "instruction_reasoning": 28.9,
                "appearance_consistency": 67.2,
                "visual_plausibility": 92.3
              }
            },
            {
              "id": "joyai-image-edit-plus",
              "name": "JoyAI-Image-Edit-Plus",
              "group": "open",
              "multi_image": true,
              "source_order": 29,
              "accuracy": {
                "temporal": 16.5,
                "causal": 16.0,
                "spatial": 20.0,
                "logical": 4.0,
                "counterfactual": 13.0,
                "hybrid": 3.0,
                "single": 11.7,
                "multi": 26.9,
                "total": 12.9
              },
              "metrics": {
                "instruction_reasoning": 26.7,
                "appearance_consistency": 76.9,
                "visual_plausibility": 92.1
              }
            },
            {
              "id": "sensenova-u1-a3b-mot-sft",
              "name": "SenseNova-U1-A3B-MoT-SFT",
              "group": "open",
              "multi_image": true,
              "source_order": 30,
              "accuracy": {
                "temporal": 20.5,
                "causal": 25.5,
                "spatial": 2.5,
                "logical": 3.0,
                "counterfactual": 17.0,
                "hybrid": 0.0,
                "single": 12.9,
                "multi": 1.3,
                "total": 12.0
              },
              "metrics": {
                "instruction_reasoning": 38.0,
                "appearance_consistency": 53.0,
                "visual_plausibility": 58.7
              }
            },
            {
              "id": "unipic-3-0",
              "name": "UniPic 3.0",
              "group": "open",
              "multi_image": true,
              "source_order": 31,
              "accuracy": {
                "temporal": 18.5,
                "causal": 17.5,
                "spatial": 18.0,
                "logical": 0.5,
                "counterfactual": 9.0,
                "hybrid": 1.0,
                "single": 11.1,
                "multi": 21.8,
                "total": 11.9
              },
              "metrics": {
                "instruction_reasoning": 28.2,
                "appearance_consistency": 60.7,
                "visual_plausibility": 83.4
              }
            },
            {
              "id": "bagel-w-cot",
              "name": "BAGEL (w/ CoT)",
              "group": "open",
              "multi_image": true,
              "source_order": 32,
              "accuracy": {
                "temporal": 18.5,
                "causal": 16.0,
                "spatial": 16.0,
                "logical": 1.5,
                "counterfactual": 10.0,
                "hybrid": 0.0,
                "single": 10.4,
                "multi": 23.1,
                "total": 11.4
              },
              "metrics": {
                "instruction_reasoning": 33.3,
                "appearance_consistency": 61.2,
                "visual_plausibility": 75.0
              }
            },
            {
              "id": "sensenova-u1-8b-mot-sft",
              "name": "SenseNova-U1-8B-MoT-SFT",
              "group": "open",
              "multi_image": true,
              "source_order": 33,
              "accuracy": {
                "temporal": 16.5,
                "causal": 22.5,
                "spatial": 7.5,
                "logical": 3.5,
                "counterfactual": 13.0,
                "hybrid": 0.0,
                "single": 12.3,
                "multi": 0.0,
                "total": 11.3
              },
              "metrics": {
                "instruction_reasoning": 36.0,
                "appearance_consistency": 58.1,
                "visual_plausibility": 60.0
              }
            },
            {
              "id": "flux-2-klein-4b",
              "name": "FLUX.2 Klein 4B",
              "group": "open",
              "multi_image": true,
              "source_order": 34,
              "accuracy": {
                "temporal": 15.5,
                "causal": 14.5,
                "spatial": 17.0,
                "logical": 2.5,
                "counterfactual": 8.0,
                "hybrid": 1.0,
                "single": 8.7,
                "multi": 35.9,
                "total": 10.8
              },
              "metrics": {
                "instruction_reasoning": 25.6,
                "appearance_consistency": 71.0,
                "visual_plausibility": 90.3
              }
            },
            {
              "id": "uniworld-v2",
              "name": "UniWorld-V2",
              "group": "open",
              "multi_image": true,
              "source_order": 35,
              "accuracy": {
                "temporal": 10.0,
                "causal": 18.0,
                "spatial": 12.0,
                "logical": 0.5,
                "counterfactual": 13.0,
                "hybrid": 1.0,
                "single": 9.9,
                "multi": 5.1,
                "total": 9.5
              },
              "metrics": {
                "instruction_reasoning": 30.7,
                "appearance_consistency": 51.6,
                "visual_plausibility": 84.7
              }
            },
            {
              "id": "bagel",
              "name": "BAGEL",
              "group": "open",
              "multi_image": true,
              "source_order": 36,
              "accuracy": {
                "temporal": 6.5,
                "causal": 6.0,
                "spatial": 8.0,
                "logical": 1.0,
                "counterfactual": 2.0,
                "hybrid": 0.0,
                "single": 3.1,
                "multi": 20.5,
                "total": 4.5
              },
              "metrics": {
                "instruction_reasoning": 23.1,
                "appearance_consistency": 47.7,
                "visual_plausibility": 76.1
              }
            },
            {
              "id": "omnigen2",
              "name": "OmniGen2",
              "group": "open",
              "multi_image": true,
              "source_order": 37,
              "accuracy": {
                "temporal": 7.0,
                "causal": 6.0,
                "spatial": 5.5,
                "logical": 0.0,
                "counterfactual": 8.0,
                "hybrid": 0.0,
                "single": 3.7,
                "multi": 14.1,
                "total": 4.5
              },
              "metrics": {
                "instruction_reasoning": 15.4,
                "appearance_consistency": 58.4,
                "visual_plausibility": 80.7
              }
            },
            {
              "id": "omnigen",
              "name": "OmniGen",
              "group": "open",
              "multi_image": true,
              "source_order": 38,
              "accuracy": {
                "temporal": 4.5,
                "causal": 4.0,
                "spatial": 5.0,
                "logical": 1.5,
                "counterfactual": 1.0,
                "hybrid": 0.0,
                "single": 2.7,
                "multi": 7.7,
                "total": 3.1
              },
              "metrics": {
                "instruction_reasoning": 13.6,
                "appearance_consistency": 44.5,
                "visual_plausibility": 61.2
              }
            },
            {
              "id": "emu2-gen",
              "name": "Emu2-Gen",
              "group": "open",
              "multi_image": true,
              "source_order": 39,
              "accuracy": {
                "temporal": 4.0,
                "causal": 1.5,
                "spatial": 0.5,
                "logical": 0.5,
                "counterfactual": 1.0,
                "hybrid": 0.0,
                "single": 1.4,
                "multi": 1.3,
                "total": 1.4
              },
              "metrics": {
                "instruction_reasoning": 10.7,
                "appearance_consistency": 25.5,
                "visual_plausibility": 62.5
              }
            },
            {
              "id": "joyai-image-edit",
              "name": "JoyAI-Image-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 40,
              "accuracy": {
                "temporal": 17.9,
                "causal": 24.0,
                "spatial": 22.0,
                "logical": 2.2,
                "counterfactual": 16.0,
                "hybrid": 2.0,
                "single": 15.0,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 31.6,
                "appearance_consistency": 71.9,
                "visual_plausibility": 90.5
              }
            },
            {
              "id": "step1x-edit-thinking",
              "name": "Step1X-Edit (thinking)",
              "group": "open",
              "multi_image": false,
              "source_order": 41,
              "accuracy": {
                "temporal": 19.6,
                "causal": 27.1,
                "spatial": 14.3,
                "logical": 0.6,
                "counterfactual": 16.0,
                "hybrid": 2.0,
                "single": 14.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 28.5,
                "appearance_consistency": 70.3,
                "visual_plausibility": 89.9
              }
            },
            {
              "id": "boogu-image-0-1-edit",
              "name": "Boogu-Image-0.1-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 42,
              "accuracy": {
                "temporal": 15.5,
                "causal": 21.9,
                "spatial": 17.6,
                "logical": 6.1,
                "counterfactual": 11.0,
                "hybrid": 3.0,
                "single": 13.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 27.5,
                "appearance_consistency": 79.8,
                "visual_plausibility": 91.0
              }
            },
            {
              "id": "step1x-edit-thinking-reflection",
              "name": "Step1X-Edit (thinking + reflection)",
              "group": "open",
              "multi_image": false,
              "source_order": 43,
              "accuracy": {
                "temporal": 21.4,
                "causal": 22.9,
                "spatial": 9.9,
                "logical": 1.7,
                "counterfactual": 19.0,
                "hybrid": 1.0,
                "single": 13.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 30.2,
                "appearance_consistency": 68.0,
                "visual_plausibility": 89.4
              }
            },
            {
              "id": "longcat-image-edit",
              "name": "LongCat-Image-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 44,
              "accuracy": {
                "temporal": 10.1,
                "causal": 20.8,
                "spatial": 15.4,
                "logical": 1.1,
                "counterfactual": 9.0,
                "hybrid": 0.0,
                "single": 10.4,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 25.7,
                "appearance_consistency": 62.0,
                "visual_plausibility": 83.9
              }
            },
            {
              "id": "step1x-edit-base",
              "name": "Step1X-Edit (base)",
              "group": "open",
              "multi_image": false,
              "source_order": 45,
              "accuracy": {
                "temporal": 13.1,
                "causal": 18.8,
                "spatial": 10.4,
                "logical": 1.1,
                "counterfactual": 14.0,
                "hybrid": 1.0,
                "single": 10.2,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 26.0,
                "appearance_consistency": 66.1,
                "visual_plausibility": 87.1
              }
            },
            {
              "id": "internvl-u-w-cot",
              "name": "InternVL-U (w/ CoT)",
              "group": "open",
              "multi_image": false,
              "source_order": 46,
              "accuracy": {
                "temporal": 8.9,
                "causal": 14.1,
                "spatial": 4.9,
                "logical": 1.1,
                "counterfactual": 16.0,
                "hybrid": 0.0,
                "single": 7.5,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 27.8,
                "appearance_consistency": 52.1,
                "visual_plausibility": 71.1
              }
            },
            {
              "id": "flux-1-kontext-dev",
              "name": "FLUX.1 Kontext Dev",
              "group": "open",
              "multi_image": false,
              "source_order": 47,
              "accuracy": {
                "temporal": 5.4,
                "causal": 9.4,
                "spatial": 12.1,
                "logical": 1.7,
                "counterfactual": 7.0,
                "hybrid": 0.0,
                "single": 6.4,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 18.6,
                "appearance_consistency": 72.8,
                "visual_plausibility": 91.0
              }
            },
            {
              "id": "llada-image",
              "name": "LLaDA-Image",
              "group": "open",
              "multi_image": false,
              "source_order": 48,
              "accuracy": {
                "temporal": 7.1,
                "causal": 4.7,
                "spatial": 3.8,
                "logical": 0.0,
                "counterfactual": 4.0,
                "hybrid": 0.0,
                "single": 3.5,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 21.7,
                "appearance_consistency": 26.7,
                "visual_plausibility": 78.0
              }
            },
            {
              "id": "ovis-u1",
              "name": "Ovis-U1",
              "group": "open",
              "multi_image": false,
              "source_order": 49,
              "accuracy": {
                "temporal": 4.8,
                "causal": 6.3,
                "spatial": 2.2,
                "logical": 1.7,
                "counterfactual": 2.0,
                "hybrid": 0.0,
                "single": 3.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 20.5,
                "appearance_consistency": 32.1,
                "visual_plausibility": 71.2
              }
            },
            {
              "id": "internvl-u",
              "name": "InternVL-U",
              "group": "open",
              "multi_image": false,
              "source_order": 50,
              "accuracy": {
                "temporal": 3.6,
                "causal": 2.6,
                "spatial": 3.8,
                "logical": 0.6,
                "counterfactual": 5.0,
                "hybrid": 0.0,
                "single": 2.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 21.0,
                "appearance_consistency": 39.7,
                "visual_plausibility": 63.4
              }
            },
            {
              "id": "unipic2-sd3-5m-kontext-2b",
              "name": "UniPic2-SD3.5M-Kontext-2B",
              "group": "open",
              "multi_image": false,
              "source_order": 51,
              "accuracy": {
                "temporal": 1.2,
                "causal": 2.1,
                "spatial": 0.5,
                "logical": 0.0,
                "counterfactual": 3.0,
                "hybrid": 0.0,
                "single": 1.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 16.2,
                "appearance_consistency": 34.4,
                "visual_plausibility": 54.2
              }
            },
            {
              "id": "lumina-dimoo",
              "name": "Lumina-DiMOO",
              "group": "open",
              "multi_image": false,
              "source_order": 52,
              "accuracy": {
                "temporal": 0.6,
                "causal": 1.6,
                "spatial": 0.0,
                "logical": 0.6,
                "counterfactual": 4.0,
                "hybrid": 0.0,
                "single": 1.0,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 11.2,
                "appearance_consistency": 46.8,
                "visual_plausibility": 63.9
              }
            },
            {
              "id": "uniworld-v1",
              "name": "UniWorld-V1",
              "group": "open",
              "multi_image": false,
              "source_order": 53,
              "accuracy": {
                "temporal": 1.2,
                "causal": 1.0,
                "spatial": 0.5,
                "logical": 0.6,
                "counterfactual": 1.0,
                "hybrid": 0.0,
                "single": 0.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 15.8,
                "appearance_consistency": 23.3,
                "visual_plausibility": 58.3
              }
            },
            {
              "id": "rise-agent-ours",
              "name": "RISE-Agent (Ours)",
              "group": "agentic",
              "multi_image": true,
              "source_order": 54,
              "accuracy": {
                "temporal": 58.5,
                "causal": 58.0,
                "spatial": 37.5,
                "logical": 39.0,
                "counterfactual": 66.0,
                "hybrid": 28.0,
                "single": 48.3,
                "multi": 44.9,
                "total": 48.0
              },
              "metrics": {
                "instruction_reasoning": 67.6,
                "appearance_consistency": 90.6,
                "visual_plausibility": 92.9
              }
            },
            {
              "id": "mindbrush",
              "name": "MindBrush",
              "group": "agentic",
              "multi_image": false,
              "source_order": 55,
              "accuracy": {
                "temporal": 35.1,
                "causal": 33.3,
                "spatial": 16.5,
                "logical": 8.9,
                "counterfactual": 32.0,
                "hybrid": 0.0,
                "single": 21.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 49.2,
                "appearance_consistency": 56.4,
                "visual_plausibility": 81.1
              }
            },
            {
              "id": "interleavethinker",
              "name": "InterleaveThinker",
              "group": "agentic",
              "multi_image": false,
              "source_order": 56,
              "accuracy": {
                "temporal": 38.7,
                "causal": 30.7,
                "spatial": 15.9,
                "logical": 1.7,
                "counterfactual": 26.0,
                "hybrid": 8.0,
                "single": 20.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 40.0,
                "appearance_consistency": 66.4,
                "visual_plausibility": 87.3
              }
            },
            {
              "id": "intentedit",
              "name": "IntentEdit",
              "group": "agentic",
              "multi_image": false,
              "source_order": 57,
              "accuracy": {
                "temporal": 23.2,
                "causal": 24.0,
                "spatial": 11.5,
                "logical": 1.1,
                "counterfactual": 14.0,
                "hybrid": 0.0,
                "single": 13.2,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 41.0,
                "appearance_consistency": 58.4,
                "visual_plausibility": 78.7
              }
            },
            {
              "id": "imagent",
              "name": "ImAgent",
              "group": "agentic",
              "multi_image": false,
              "source_order": 58,
              "accuracy": {
                "temporal": 5.4,
                "causal": 4.7,
                "spatial": 4.4,
                "logical": 0.6,
                "counterfactual": 5.0,
                "hybrid": 0.0,
                "single": 3.5,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 24.6,
                "appearance_consistency": 29.2,
                "visual_plausibility": 65.4
              }
            }
          ]
        },
        "zh": {
          "language": "Chinese",
          "language_code": "zh",
          "model_count": 58,
          "groups": [
            {
              "id": "closed",
              "label": "Closed-source Models",
              "count": 19
            },
            {
              "id": "open",
              "label": "Open-source Models",
              "count": 34
            },
            {
              "id": "agentic",
              "label": "Agentic Methods",
              "count": 5
            }
          ],
          "models": [
            {
              "id": "gpt-image-2-5-sunburst",
              "name": "GPT-Image-2.5 Sunburst",
              "group": "closed",
              "multi_image": true,
              "source_order": 1,
              "accuracy": {
                "temporal": 62.5,
                "causal": 70.5,
                "spatial": 63.0,
                "logical": 29.0,
                "counterfactual": 69.0,
                "hybrid": 36.0,
                "single": 56.0,
                "multi": 50.0,
                "total": 55.5
              },
              "metrics": {
                "instruction_reasoning": 67.6,
                "appearance_consistency": 96.7,
                "visual_plausibility": 97.9
              }
            },
            {
              "id": "nano-banana-pro",
              "name": "Nano Banana Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 2,
              "accuracy": {
                "temporal": 62.5,
                "causal": 67.0,
                "spatial": 50.5,
                "logical": 38.5,
                "counterfactual": 50.0,
                "hybrid": 27.0,
                "single": 52.4,
                "multi": 39.7,
                "total": 51.4
              },
              "metrics": {
                "instruction_reasoning": 70.6,
                "appearance_consistency": 88.6,
                "visual_plausibility": 96.5
              }
            },
            {
              "id": "nano-banana-2",
              "name": "Nano Banana 2",
              "group": "closed",
              "multi_image": true,
              "source_order": 3,
              "accuracy": {
                "temporal": 62.0,
                "causal": 69.0,
                "spatial": 50.0,
                "logical": 31.5,
                "counterfactual": 57.0,
                "hybrid": 28.0,
                "single": 51.7,
                "multi": 42.3,
                "total": 51.0
              },
              "metrics": {
                "instruction_reasoning": 69.7,
                "appearance_consistency": 88.9,
                "visual_plausibility": 96.8
              }
            },
            {
              "id": "luma-uni-1",
              "name": "Luma Uni-1",
              "group": "closed",
              "multi_image": true,
              "source_order": 4,
              "accuracy": {
                "temporal": 65.5,
                "causal": 67.0,
                "spatial": 53.5,
                "logical": 17.0,
                "counterfactual": 56.0,
                "hybrid": 24.0,
                "single": 49.1,
                "multi": 42.3,
                "total": 48.6
              },
              "metrics": {
                "instruction_reasoning": 63.2,
                "appearance_consistency": 89.5,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "gpt-image-2",
              "name": "GPT-Image-2",
              "group": "closed",
              "multi_image": true,
              "source_order": 5,
              "accuracy": {
                "temporal": 57.0,
                "causal": 62.0,
                "spatial": 54.5,
                "logical": 20.5,
                "counterfactual": 61.0,
                "hybrid": 20.0,
                "single": 46.9,
                "multi": 47.4,
                "total": 46.9
              },
              "metrics": {
                "instruction_reasoning": 61.1,
                "appearance_consistency": 91.1,
                "visual_plausibility": 97.7
              }
            },
            {
              "id": "qwen-image-3-0",
              "name": "Qwen-Image-3.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 6,
              "accuracy": {
                "temporal": 58.0,
                "causal": 50.0,
                "spatial": 43.0,
                "logical": 39.0,
                "counterfactual": 49.0,
                "hybrid": 34.0,
                "single": 46.1,
                "multi": 48.7,
                "total": 46.3
              },
              "metrics": {
                "instruction_reasoning": 67.8,
                "appearance_consistency": 85.6,
                "visual_plausibility": 95.3
              }
            },
            {
              "id": "gpt-image-2-5-flare",
              "name": "GPT-Image-2.5 Flare",
              "group": "closed",
              "multi_image": true,
              "source_order": 7,
              "accuracy": {
                "temporal": 52.0,
                "causal": 66.0,
                "spatial": 54.0,
                "logical": 14.0,
                "counterfactual": 61.0,
                "hybrid": 19.0,
                "single": 46.3,
                "multi": 32.1,
                "total": 45.2
              },
              "metrics": {
                "instruction_reasoning": 58.9,
                "appearance_consistency": 93.4,
                "visual_plausibility": 97.6
              }
            },
            {
              "id": "flux-2-max",
              "name": "FLUX.2 Max",
              "group": "closed",
              "multi_image": true,
              "source_order": 8,
              "accuracy": {
                "temporal": 59.5,
                "causal": 59.0,
                "spatial": 42.0,
                "logical": 14.0,
                "counterfactual": 72.0,
                "hybrid": 18.0,
                "single": 44.4,
                "multi": 38.5,
                "total": 43.9
              },
              "metrics": {
                "instruction_reasoning": 61.1,
                "appearance_consistency": 83.0,
                "visual_plausibility": 95.8
              }
            },
            {
              "id": "nano-banana-2-lite",
              "name": "Nano Banana 2 Lite",
              "group": "closed",
              "multi_image": true,
              "source_order": 9,
              "accuracy": {
                "temporal": 58.5,
                "causal": 60.5,
                "spatial": 41.5,
                "logical": 12.0,
                "counterfactual": 59.0,
                "hybrid": 18.0,
                "single": 42.5,
                "multi": 38.5,
                "total": 42.2
              },
              "metrics": {
                "instruction_reasoning": 58.7,
                "appearance_consistency": 88.3,
                "visual_plausibility": 97.0
              }
            },
            {
              "id": "gpt-image-1-5",
              "name": "GPT-Image-1.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 10,
              "accuracy": {
                "temporal": 55.0,
                "causal": 57.0,
                "spatial": 35.5,
                "logical": 4.5,
                "counterfactual": 57.0,
                "hybrid": 10.0,
                "single": 37.9,
                "multi": 28.2,
                "total": 37.1
              },
              "metrics": {
                "instruction_reasoning": 55.7,
                "appearance_consistency": 80.5,
                "visual_plausibility": 96.2
              }
            },
            {
              "id": "nano-banana",
              "name": "Nano Banana",
              "group": "closed",
              "multi_image": true,
              "source_order": 11,
              "accuracy": {
                "temporal": 49.5,
                "causal": 53.0,
                "spatial": 40.0,
                "logical": 12.0,
                "counterfactual": 52.0,
                "hybrid": 5.0,
                "single": 36.6,
                "multi": 37.2,
                "total": 36.6
              },
              "metrics": {
                "instruction_reasoning": 53.8,
                "appearance_consistency": 83.8,
                "visual_plausibility": 96.3
              }
            },
            {
              "id": "flux-2-pro",
              "name": "FLUX.2 Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 12,
              "accuracy": {
                "temporal": 51.0,
                "causal": 44.5,
                "spatial": 38.5,
                "logical": 8.0,
                "counterfactual": 51.0,
                "hybrid": 11.0,
                "single": 33.5,
                "multi": 47.4,
                "total": 34.6
              },
              "metrics": {
                "instruction_reasoning": 56.1,
                "appearance_consistency": 73.7,
                "visual_plausibility": 95.1
              }
            },
            {
              "id": "hunyuanimage-3-5",
              "name": "HunyuanImage-3.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 13,
              "accuracy": {
                "temporal": 44.0,
                "causal": 39.5,
                "spatial": 45.0,
                "logical": 14.0,
                "counterfactual": 42.0,
                "hybrid": 13.0,
                "single": 33.3,
                "multi": 42.3,
                "total": 34.0
              },
              "metrics": {
                "instruction_reasoning": 51.2,
                "appearance_consistency": 93.3,
                "visual_plausibility": 94.4
              }
            },
            {
              "id": "wan2-7-image-pro",
              "name": "Wan2.7-Image-Pro",
              "group": "closed",
              "multi_image": true,
              "source_order": 14,
              "accuracy": {
                "temporal": 40.5,
                "causal": 44.5,
                "spatial": 37.5,
                "logical": 9.5,
                "counterfactual": 47.0,
                "hybrid": 13.0,
                "single": 32.4,
                "multi": 32.1,
                "total": 32.4
              },
              "metrics": {
                "instruction_reasoning": 50.4,
                "appearance_consistency": 85.3,
                "visual_plausibility": 93.1
              }
            },
            {
              "id": "qwen-image-2-0",
              "name": "Qwen-Image-2.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 15,
              "accuracy": {
                "temporal": 51.5,
                "causal": 37.0,
                "spatial": 30.5,
                "logical": 9.0,
                "counterfactual": 37.0,
                "hybrid": 1.0,
                "single": 28.7,
                "multi": 37.2,
                "total": 29.4
              },
              "metrics": {
                "instruction_reasoning": 49.5,
                "appearance_consistency": 77.4,
                "visual_plausibility": 90.9
              }
            },
            {
              "id": "seedream-4-5",
              "name": "Seedream 4.5",
              "group": "closed",
              "multi_image": true,
              "source_order": 16,
              "accuracy": {
                "temporal": 44.0,
                "causal": 45.0,
                "spatial": 26.5,
                "logical": 8.5,
                "counterfactual": 35.0,
                "hybrid": 10.0,
                "single": 29.9,
                "multi": 21.8,
                "total": 29.3
              },
              "metrics": {
                "instruction_reasoning": 50.6,
                "appearance_consistency": 78.1,
                "visual_plausibility": 94.8
              }
            },
            {
              "id": "seedream-5-0",
              "name": "Seedream 5.0",
              "group": "closed",
              "multi_image": true,
              "source_order": 17,
              "accuracy": {
                "temporal": 40.5,
                "causal": 39.5,
                "spatial": 28.0,
                "logical": 11.5,
                "counterfactual": 30.0,
                "hybrid": 7.0,
                "single": 27.7,
                "multi": 26.9,
                "total": 27.6
              },
              "metrics": {
                "instruction_reasoning": 49.1,
                "appearance_consistency": 73.2,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "gpt-image-1",
              "name": "GPT-Image-1",
              "group": "closed",
              "multi_image": true,
              "source_order": 18,
              "accuracy": {
                "temporal": 43.5,
                "causal": 40.0,
                "spatial": 24.5,
                "logical": 5.5,
                "counterfactual": 37.0,
                "hybrid": 8.0,
                "single": 28.1,
                "multi": 16.7,
                "total": 27.2
              },
              "metrics": {
                "instruction_reasoning": 50.1,
                "appearance_consistency": 72.7,
                "visual_plausibility": 94.8
              }
            },
            {
              "id": "step-image-edit-2",
              "name": "Step Image Edit 2",
              "group": "closed",
              "multi_image": false,
              "source_order": 19,
              "accuracy": {
                "temporal": 14.9,
                "causal": 19.3,
                "spatial": 22.5,
                "logical": 2.2,
                "counterfactual": 12.0,
                "hybrid": 0.0,
                "single": 12.9,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 29.8,
                "appearance_consistency": 67.9,
                "visual_plausibility": 84.9
              }
            },
            {
              "id": "hunyuanimage-3-0-instruct",
              "name": "HunyuanImage-3.0-Instruct",
              "group": "open",
              "multi_image": true,
              "source_order": 20,
              "accuracy": {
                "temporal": 28.0,
                "causal": 32.0,
                "spatial": 35.0,
                "logical": 8.5,
                "counterfactual": 20.0,
                "hybrid": 0.0,
                "single": 22.3,
                "multi": 26.9,
                "total": 22.7
              },
              "metrics": {
                "instruction_reasoning": 38.9,
                "appearance_consistency": 75.4,
                "visual_plausibility": 87.1
              }
            },
            {
              "id": "qwen-image-2-1",
              "name": "Qwen-Image-2.1",
              "group": "open",
              "multi_image": true,
              "source_order": 21,
              "accuracy": {
                "temporal": 22.5,
                "causal": 23.0,
                "spatial": 25.0,
                "logical": 6.5,
                "counterfactual": 16.0,
                "hybrid": 0.0,
                "single": 15.8,
                "multi": 30.8,
                "total": 17.0
              },
              "metrics": {
                "instruction_reasoning": 33.2,
                "appearance_consistency": 77.7,
                "visual_plausibility": 85.7
              }
            },
            {
              "id": "firered-image-edit-1-1",
              "name": "FireRed-Image-Edit-1.1",
              "group": "open",
              "multi_image": true,
              "source_order": 22,
              "accuracy": {
                "temporal": 21.0,
                "causal": 24.5,
                "spatial": 25.0,
                "logical": 1.0,
                "counterfactual": 15.0,
                "hybrid": 4.0,
                "single": 15.6,
                "multi": 23.1,
                "total": 16.2
              },
              "metrics": {
                "instruction_reasoning": 32.8,
                "appearance_consistency": 63.8,
                "visual_plausibility": 92.0
              }
            },
            {
              "id": "flux-2-dev",
              "name": "FLUX.2 Dev",
              "group": "open",
              "multi_image": true,
              "source_order": 23,
              "accuracy": {
                "temporal": 21.0,
                "causal": 26.0,
                "spatial": 16.5,
                "logical": 1.5,
                "counterfactual": 13.0,
                "hybrid": 4.0,
                "single": 13.3,
                "multi": 30.8,
                "total": 14.7
              },
              "metrics": {
                "instruction_reasoning": 31.0,
                "appearance_consistency": 57.8,
                "visual_plausibility": 93.5
              }
            },
            {
              "id": "qwen-image-edit-2511",
              "name": "Qwen-Image-Edit-2511",
              "group": "open",
              "multi_image": true,
              "source_order": 24,
              "accuracy": {
                "temporal": 19.5,
                "causal": 19.5,
                "spatial": 23.0,
                "logical": 2.0,
                "counterfactual": 10.0,
                "hybrid": 0.0,
                "single": 13.7,
                "multi": 15.4,
                "total": 13.8
              },
              "metrics": {
                "instruction_reasoning": 32.8,
                "appearance_consistency": 57.6,
                "visual_plausibility": 85.4
              }
            },
            {
              "id": "qwen-image-edit-2509",
              "name": "Qwen-Image-Edit-2509",
              "group": "open",
              "multi_image": true,
              "source_order": 25,
              "accuracy": {
                "temporal": 17.5,
                "causal": 19.0,
                "spatial": 21.5,
                "logical": 1.5,
                "counterfactual": 15.0,
                "hybrid": 3.0,
                "single": 13.7,
                "multi": 14.1,
                "total": 13.7
              },
              "metrics": {
                "instruction_reasoning": 30.9,
                "appearance_consistency": 53.6,
                "visual_plausibility": 83.7
              }
            },
            {
              "id": "firered-image-edit-1-0",
              "name": "FireRed-Image-Edit-1.0",
              "group": "open",
              "multi_image": true,
              "source_order": 26,
              "accuracy": {
                "temporal": 19.5,
                "causal": 16.5,
                "spatial": 25.0,
                "logical": 0.5,
                "counterfactual": 11.0,
                "hybrid": 2.0,
                "single": 13.2,
                "multi": 17.9,
                "total": 13.6
              },
              "metrics": {
                "instruction_reasoning": 31.9,
                "appearance_consistency": 59.8,
                "visual_plausibility": 94.0
              }
            },
            {
              "id": "sensenova-u1-a3b-mot-sft",
              "name": "SenseNova-U1-A3B-MoT-SFT",
              "group": "open",
              "multi_image": true,
              "source_order": 27,
              "accuracy": {
                "temporal": 21.5,
                "causal": 28.0,
                "spatial": 7.0,
                "logical": 3.0,
                "counterfactual": 11.0,
                "hybrid": 0.0,
                "single": 14.0,
                "multi": 1.3,
                "total": 13.0
              },
              "metrics": {
                "instruction_reasoning": 38.3,
                "appearance_consistency": 54.3,
                "visual_plausibility": 57.5
              }
            },
            {
              "id": "joyai-image-edit-plus",
              "name": "JoyAI-Image-Edit-Plus",
              "group": "open",
              "multi_image": true,
              "source_order": 28,
              "accuracy": {
                "temporal": 14.5,
                "causal": 19.5,
                "spatial": 19.0,
                "logical": 5.0,
                "counterfactual": 9.0,
                "hybrid": 4.0,
                "single": 11.2,
                "multi": 33.3,
                "total": 12.9
              },
              "metrics": {
                "instruction_reasoning": 26.0,
                "appearance_consistency": 78.8,
                "visual_plausibility": 91.6
              }
            },
            {
              "id": "flux-2-klein-9b",
              "name": "FLUX.2 Klein 9B",
              "group": "open",
              "multi_image": true,
              "source_order": 29,
              "accuracy": {
                "temporal": 22.0,
                "causal": 16.0,
                "spatial": 16.5,
                "logical": 3.5,
                "counterfactual": 9.0,
                "hybrid": 3.0,
                "single": 11.1,
                "multi": 33.3,
                "total": 12.8
              },
              "metrics": {
                "instruction_reasoning": 28.8,
                "appearance_consistency": 65.7,
                "visual_plausibility": 91.2
              }
            },
            {
              "id": "bagel-w-cot",
              "name": "BAGEL (w/ CoT)",
              "group": "open",
              "multi_image": true,
              "source_order": 30,
              "accuracy": {
                "temporal": 19.0,
                "causal": 18.0,
                "spatial": 16.5,
                "logical": 0.0,
                "counterfactual": 6.0,
                "hybrid": 0.0,
                "single": 9.8,
                "multi": 29.5,
                "total": 11.3
              },
              "metrics": {
                "instruction_reasoning": 31.8,
                "appearance_consistency": 61.0,
                "visual_plausibility": 73.6
              }
            },
            {
              "id": "hidream-o1-image",
              "name": "HiDream-O1-Image",
              "group": "open",
              "multi_image": true,
              "source_order": 31,
              "accuracy": {
                "temporal": 18.5,
                "causal": 13.5,
                "spatial": 17.5,
                "logical": 0.5,
                "counterfactual": 7.0,
                "hybrid": 0.0,
                "single": 8.8,
                "multi": 33.3,
                "total": 10.7
              },
              "metrics": {
                "instruction_reasoning": 27.1,
                "appearance_consistency": 54.6,
                "visual_plausibility": 84.4
              }
            },
            {
              "id": "flux-2-klein-4b",
              "name": "FLUX.2 Klein 4B",
              "group": "open",
              "multi_image": true,
              "source_order": 32,
              "accuracy": {
                "temporal": 16.5,
                "causal": 12.5,
                "spatial": 14.5,
                "logical": 4.0,
                "counterfactual": 10.0,
                "hybrid": 1.0,
                "single": 8.0,
                "multi": 41.0,
                "total": 10.6
              },
              "metrics": {
                "instruction_reasoning": 26.1,
                "appearance_consistency": 72.2,
                "visual_plausibility": 90.1
              }
            },
            {
              "id": "uniworld-v2",
              "name": "UniWorld-V2",
              "group": "open",
              "multi_image": true,
              "source_order": 33,
              "accuracy": {
                "temporal": 13.5,
                "causal": 17.0,
                "spatial": 15.5,
                "logical": 0.0,
                "counterfactual": 12.0,
                "hybrid": 1.0,
                "single": 10.7,
                "multi": 7.7,
                "total": 10.5
              },
              "metrics": {
                "instruction_reasoning": 30.6,
                "appearance_consistency": 46.0,
                "visual_plausibility": 85.8
              }
            },
            {
              "id": "sensenova-u1-8b-mot-sft",
              "name": "SenseNova-U1-8B-MoT-SFT",
              "group": "open",
              "multi_image": true,
              "source_order": 34,
              "accuracy": {
                "temporal": 16.0,
                "causal": 21.0,
                "spatial": 3.5,
                "logical": 3.5,
                "counterfactual": 15.0,
                "hybrid": 0.0,
                "single": 11.1,
                "multi": 1.3,
                "total": 10.3
              },
              "metrics": {
                "instruction_reasoning": 34.6,
                "appearance_consistency": 57.3,
                "visual_plausibility": 60.2
              }
            },
            {
              "id": "unipic-3-0",
              "name": "UniPic 3.0",
              "group": "open",
              "multi_image": true,
              "source_order": 35,
              "accuracy": {
                "temporal": 7.0,
                "causal": 14.0,
                "spatial": 12.5,
                "logical": 0.0,
                "counterfactual": 7.0,
                "hybrid": 0.0,
                "single": 7.5,
                "multi": 6.4,
                "total": 7.4
              },
              "metrics": {
                "instruction_reasoning": 24.8,
                "appearance_consistency": 55.4,
                "visual_plausibility": 80.0
              }
            },
            {
              "id": "bagel",
              "name": "BAGEL",
              "group": "open",
              "multi_image": true,
              "source_order": 36,
              "accuracy": {
                "temporal": 10.0,
                "causal": 7.0,
                "spatial": 10.0,
                "logical": 1.0,
                "counterfactual": 8.0,
                "hybrid": 0.0,
                "single": 4.8,
                "multi": 25.6,
                "total": 6.4
              },
              "metrics": {
                "instruction_reasoning": 26.3,
                "appearance_consistency": 54.9,
                "visual_plausibility": 75.2
              }
            },
            {
              "id": "omnigen2",
              "name": "OmniGen2",
              "group": "open",
              "multi_image": true,
              "source_order": 37,
              "accuracy": {
                "temporal": 6.0,
                "causal": 5.5,
                "spatial": 6.0,
                "logical": 0.0,
                "counterfactual": 6.0,
                "hybrid": 0.0,
                "single": 2.9,
                "multi": 17.9,
                "total": 4.1
              },
              "metrics": {
                "instruction_reasoning": 14.7,
                "appearance_consistency": 57.6,
                "visual_plausibility": 81.5
              }
            },
            {
              "id": "omnigen",
              "name": "OmniGen",
              "group": "open",
              "multi_image": true,
              "source_order": 38,
              "accuracy": {
                "temporal": 7.0,
                "causal": 2.5,
                "spatial": 5.0,
                "logical": 3.0,
                "counterfactual": 4.0,
                "hybrid": 0.0,
                "single": 2.7,
                "multi": 17.9,
                "total": 3.9
              },
              "metrics": {
                "instruction_reasoning": 12.1,
                "appearance_consistency": 58.4,
                "visual_plausibility": 74.7
              }
            },
            {
              "id": "emu2-gen",
              "name": "Emu2-Gen",
              "group": "open",
              "multi_image": true,
              "source_order": 39,
              "accuracy": {
                "temporal": 2.5,
                "causal": 1.0,
                "spatial": 1.0,
                "logical": 0.0,
                "counterfactual": 2.0,
                "hybrid": 0.0,
                "single": 1.0,
                "multi": 2.6,
                "total": 1.1
              },
              "metrics": {
                "instruction_reasoning": 10.0,
                "appearance_consistency": 25.7,
                "visual_plausibility": 64.7
              }
            },
            {
              "id": "joyai-image-edit",
              "name": "JoyAI-Image-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 40,
              "accuracy": {
                "temporal": 13.7,
                "causal": 24.0,
                "spatial": 15.4,
                "logical": 1.1,
                "counterfactual": 21.0,
                "hybrid": 4.0,
                "single": 13.4,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 30.6,
                "appearance_consistency": 70.4,
                "visual_plausibility": 91.4
              }
            },
            {
              "id": "boogu-image-0-1-edit",
              "name": "Boogu-Image-0.1-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 41,
              "accuracy": {
                "temporal": 13.1,
                "causal": 22.4,
                "spatial": 17.0,
                "logical": 2.2,
                "counterfactual": 17.0,
                "hybrid": 1.0,
                "single": 12.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 27.1,
                "appearance_consistency": 80.7,
                "visual_plausibility": 91.6
              }
            },
            {
              "id": "step1x-edit-thinking-reflection",
              "name": "Step1X-Edit (thinking + reflection)",
              "group": "open",
              "multi_image": false,
              "source_order": 42,
              "accuracy": {
                "temporal": 17.3,
                "causal": 18.2,
                "spatial": 11.0,
                "logical": 1.1,
                "counterfactual": 14.0,
                "hybrid": 2.0,
                "single": 11.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 26.3,
                "appearance_consistency": 65.7,
                "visual_plausibility": 89.2
              }
            },
            {
              "id": "step1x-edit-thinking",
              "name": "Step1X-Edit (thinking)",
              "group": "open",
              "multi_image": false,
              "source_order": 43,
              "accuracy": {
                "temporal": 14.3,
                "causal": 15.1,
                "spatial": 13.2,
                "logical": 2.2,
                "counterfactual": 17.0,
                "hybrid": 2.0,
                "single": 10.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 25.5,
                "appearance_consistency": 67.5,
                "visual_plausibility": 88.7
              }
            },
            {
              "id": "step1x-edit-base",
              "name": "Step1X-Edit (base)",
              "group": "open",
              "multi_image": false,
              "source_order": 44,
              "accuracy": {
                "temporal": 13.1,
                "causal": 16.1,
                "spatial": 12.6,
                "logical": 0.6,
                "counterfactual": 15.0,
                "hybrid": 1.0,
                "single": 10.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 24.2,
                "appearance_consistency": 68.1,
                "visual_plausibility": 86.6
              }
            },
            {
              "id": "longcat-image-edit",
              "name": "LongCat-Image-Edit",
              "group": "open",
              "multi_image": false,
              "source_order": 45,
              "accuracy": {
                "temporal": 13.7,
                "causal": 16.1,
                "spatial": 13.2,
                "logical": 1.1,
                "counterfactual": 9.0,
                "hybrid": 0.0,
                "single": 9.7,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 27.5,
                "appearance_consistency": 55.8,
                "visual_plausibility": 84.4
              }
            },
            {
              "id": "flux-1-kontext-dev",
              "name": "FLUX.1 Kontext Dev",
              "group": "open",
              "multi_image": false,
              "source_order": 46,
              "accuracy": {
                "temporal": 3.0,
                "causal": 3.6,
                "spatial": 3.8,
                "logical": 3.3,
                "counterfactual": 7.0,
                "hybrid": 1.0,
                "single": 3.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 9.8,
                "appearance_consistency": 70.7,
                "visual_plausibility": 82.9
              }
            },
            {
              "id": "llada-image",
              "name": "LLaDA-Image",
              "group": "open",
              "multi_image": false,
              "source_order": 47,
              "accuracy": {
                "temporal": 4.8,
                "causal": 5.7,
                "spatial": 2.2,
                "logical": 0.6,
                "counterfactual": 8.0,
                "hybrid": 0.0,
                "single": 3.5,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 20.2,
                "appearance_consistency": 25.0,
                "visual_plausibility": 81.0
              }
            },
            {
              "id": "internvl-u-w-cot",
              "name": "InternVL-U (w/ CoT)",
              "group": "open",
              "multi_image": false,
              "source_order": 48,
              "accuracy": {
                "temporal": 6.0,
                "causal": 3.1,
                "spatial": 2.2,
                "logical": 0.0,
                "counterfactual": 4.0,
                "hybrid": 1.0,
                "single": 2.7,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 20.4,
                "appearance_consistency": 41.4,
                "visual_plausibility": 66.4
              }
            },
            {
              "id": "ovis-u1",
              "name": "Ovis-U1",
              "group": "open",
              "multi_image": false,
              "source_order": 49,
              "accuracy": {
                "temporal": 3.6,
                "causal": 5.7,
                "spatial": 2.2,
                "logical": 0.6,
                "counterfactual": 2.0,
                "hybrid": 0.0,
                "single": 2.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 16.9,
                "appearance_consistency": 41.1,
                "visual_plausibility": 67.3
              }
            },
            {
              "id": "internvl-u",
              "name": "InternVL-U",
              "group": "open",
              "multi_image": false,
              "source_order": 50,
              "accuracy": {
                "temporal": 3.6,
                "causal": 4.2,
                "spatial": 1.1,
                "logical": 0.6,
                "counterfactual": 5.0,
                "hybrid": 0.0,
                "single": 2.4,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 19.5,
                "appearance_consistency": 39.3,
                "visual_plausibility": 68.1
              }
            },
            {
              "id": "lumina-dimoo",
              "name": "Lumina-DiMOO",
              "group": "open",
              "multi_image": false,
              "source_order": 51,
              "accuracy": {
                "temporal": 1.8,
                "causal": 2.6,
                "spatial": 2.2,
                "logical": 2.2,
                "counterfactual": 4.0,
                "hybrid": 0.0,
                "single": 2.2,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 10.9,
                "appearance_consistency": 49.6,
                "visual_plausibility": 60.7
              }
            },
            {
              "id": "uniworld-v1",
              "name": "UniWorld-V1",
              "group": "open",
              "multi_image": false,
              "source_order": 52,
              "accuracy": {
                "temporal": 3.0,
                "causal": 1.0,
                "spatial": 1.6,
                "logical": 0.0,
                "counterfactual": 3.0,
                "hybrid": 0.0,
                "single": 1.4,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 10.7,
                "appearance_consistency": 25.1,
                "visual_plausibility": 56.8
              }
            },
            {
              "id": "unipic2-sd3-5m-kontext-2b",
              "name": "UniPic2-SD3.5M-Kontext-2B",
              "group": "open",
              "multi_image": false,
              "source_order": 53,
              "accuracy": {
                "temporal": 0.0,
                "causal": 1.0,
                "spatial": 1.6,
                "logical": 1.1,
                "counterfactual": 2.0,
                "hybrid": 1.0,
                "single": 1.1,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 10.3,
                "appearance_consistency": 37.9,
                "visual_plausibility": 48.4
              }
            },
            {
              "id": "rise-agent-ours",
              "name": "RISE-Agent (Ours)",
              "group": "agentic",
              "multi_image": true,
              "source_order": 54,
              "accuracy": {
                "temporal": 51.0,
                "causal": 57.0,
                "spatial": 34.0,
                "logical": 25.0,
                "counterfactual": 54.0,
                "hybrid": 15.0,
                "single": 40.6,
                "multi": 37.2,
                "total": 40.3
              },
              "metrics": {
                "instruction_reasoning": 63.8,
                "appearance_consistency": 85.3,
                "visual_plausibility": 93.4
              }
            },
            {
              "id": "mindbrush",
              "name": "MindBrush",
              "group": "agentic",
              "multi_image": false,
              "source_order": 55,
              "accuracy": {
                "temporal": 43.5,
                "causal": 33.9,
                "spatial": 19.8,
                "logical": 4.4,
                "counterfactual": 36.0,
                "hybrid": 0.0,
                "single": 23.6,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 49.9,
                "appearance_consistency": 61.2,
                "visual_plausibility": 80.0
              }
            },
            {
              "id": "interleavethinker",
              "name": "InterleaveThinker",
              "group": "agentic",
              "multi_image": false,
              "source_order": 56,
              "accuracy": {
                "temporal": 25.0,
                "causal": 28.1,
                "spatial": 19.2,
                "logical": 0.6,
                "counterfactual": 28.0,
                "hybrid": 4.0,
                "single": 17.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 36.9,
                "appearance_consistency": 60.7,
                "visual_plausibility": 82.7
              }
            },
            {
              "id": "intentedit",
              "name": "IntentEdit",
              "group": "agentic",
              "multi_image": false,
              "source_order": 57,
              "accuracy": {
                "temporal": 22.6,
                "causal": 24.0,
                "spatial": 14.3,
                "logical": 1.7,
                "counterfactual": 14.0,
                "hybrid": 0.0,
                "single": 13.8,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 41.1,
                "appearance_consistency": 58.3,
                "visual_plausibility": 76.7
              }
            },
            {
              "id": "imagent",
              "name": "ImAgent",
              "group": "agentic",
              "multi_image": false,
              "source_order": 58,
              "accuracy": {
                "temporal": 4.2,
                "causal": 3.6,
                "spatial": 2.2,
                "logical": 0.0,
                "counterfactual": 2.0,
                "hybrid": 0.0,
                "single": 2.2,
                "multi": null,
                "total": null
              },
              "metrics": {
                "instruction_reasoning": 24.2,
                "appearance_consistency": 23.3,
                "visual_plausibility": 65.1
              }
            }
          ]
        }
      }
    },
    {
      "id": "risebench",
      "name": "RISEBench",
      "case_count": 360,
      "available_result_languages": [
        "en"
      ],
      "accuracy_unit": "%",
      "metric_unit": "/100",
      "score_decimals": 1,
      "default_sort": "total",
      "dimensions": [
        {
          "key": "temporal",
          "label": "Temporal",
          "description": "Infer how a scene changes over time."
        },
        {
          "key": "causal",
          "label": "Causal",
          "description": "Reason about causes, actions, and their consequences."
        },
        {
          "key": "spatial",
          "label": "Spatial",
          "description": "Reason about spatial relationships and transformations."
        },
        {
          "key": "logical",
          "label": "Logical",
          "description": "Apply explicit rules, patterns, and logical constraints."
        }
      ],
      "metrics": [
        {
          "key": "instruction_reasoning",
          "label": "Instruction Reasoning",
          "description": "Whether the edit realizes the intended reasoning outcome."
        },
        {
          "key": "appearance_consistency",
          "label": "Appearance Consistency",
          "description": "Whether content that should remain unchanged is preserved."
        },
        {
          "key": "visual_plausibility",
          "label": "Visual Plausibility",
          "description": "Visual quality and plausibility; logical tasks are excluded."
        }
      ],
      "accuracy_columns": [
        {
          "key": "temporal",
          "label": "Temporal",
          "description": "Infer how a scene changes over time."
        },
        {
          "key": "causal",
          "label": "Causal",
          "description": "Reason about causes, actions, and their consequences."
        },
        {
          "key": "spatial",
          "label": "Spatial",
          "description": "Reason about spatial relationships and transformations."
        },
        {
          "key": "logical",
          "label": "Logical",
          "description": "Apply explicit rules, patterns, and logical constraints."
        },
        {
          "key": "total",
          "label": "Overall",
          "description": "Accuracy on the complete RISEBench-360 benchmark."
        }
      ],
      "links": {
        "paper": "https://arxiv.org/abs/2504.02826",
        "data": "https://huggingface.co/datasets/PhoenixZ/RISEBench",
        "outputs": "https://huggingface.co/datasets/zpy777/RISEBench_Outputs",
        "github": "https://github.com/VisionXLab/RISEBench/tree/main/RISEBench"
      },
      "judges": {
        "instruction_reasoning": "GPT-4o",
        "appearance_consistency": "GPT-4o",
        "visual_plausibility": "GPT-4o"
      },
      "results_by_language": {
        "en": {
          "language": "Original published results",
          "language_code": "en",
          "model_count": 20,
          "groups": [],
          "models": [
            {
              "id": "gpt-image-1-5",
              "name": "GPT-Image-1.5",
              "group": null,
              "multi_image": null,
              "source_order": 1,
              "accuracy": {
                "temporal": 57.6,
                "causal": 62.2,
                "spatial": 62.0,
                "logical": 21.2,
                "total": 51.4
              },
              "metrics": {
                "instruction_reasoning": 69.7,
                "appearance_consistency": 92.5,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "gpt-image-2",
              "name": "GPT-Image-2",
              "group": null,
              "multi_image": null,
              "source_order": 2,
              "accuracy": {
                "temporal": 45.9,
                "causal": 66.7,
                "spatial": 50.0,
                "logical": 34.1,
                "total": 49.4
              },
              "metrics": {
                "instruction_reasoning": 73.8,
                "appearance_consistency": 89.3,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "gemini-3-pro-image-preview-nano-banana-pro",
              "name": "Gemini-3-pro-image-preview (Nano Banana-pro)",
              "group": null,
              "multi_image": null,
              "source_order": 3,
              "accuracy": {
                "temporal": 43.5,
                "causal": 63.3,
                "spatial": 48.0,
                "logical": 37.6,
                "total": 48.3
              },
              "metrics": {
                "instruction_reasoning": 77.0,
                "appearance_consistency": 85.5,
                "visual_plausibility": 94.4
              }
            },
            {
              "id": "gemini-2-5-flash-image-nano-banana",
              "name": "Gemini-2.5-Flash-Image (Nano Banana)",
              "group": null,
              "multi_image": null,
              "source_order": 4,
              "accuracy": {
                "temporal": 29.4,
                "causal": 48.9,
                "spatial": 37.0,
                "logical": 18.8,
                "total": 33.9
              },
              "metrics": {
                "instruction_reasoning": 61.2,
                "appearance_consistency": 86.0,
                "visual_plausibility": 91.3
              }
            },
            {
              "id": "gpt-image-1",
              "name": "GPT-Image-1",
              "group": null,
              "multi_image": null,
              "source_order": 5,
              "accuracy": {
                "temporal": 36.5,
                "causal": 34.4,
                "spatial": 37.0,
                "logical": 10.6,
                "total": 30.0
              },
              "metrics": {
                "instruction_reasoning": 62.8,
                "appearance_consistency": 80.2,
                "visual_plausibility": 94.9
              }
            },
            {
              "id": "gpt-image-1-mini",
              "name": "GPT-Image-1-mini",
              "group": null,
              "multi_image": null,
              "source_order": 6,
              "accuracy": {
                "temporal": 25.9,
                "causal": 31.1,
                "spatial": 33.0,
                "logical": 9.4,
                "total": 25.3
              },
              "metrics": {
                "instruction_reasoning": 54.1,
                "appearance_consistency": 71.5,
                "visual_plausibility": 93.7
              }
            },
            {
              "id": "qwen-image-edit-2511",
              "name": "Qwen-Image-Edit-2511",
              "group": null,
              "multi_image": null,
              "source_order": 7,
              "accuracy": {
                "temporal": 21.2,
                "causal": 18.9,
                "spatial": 31.0,
                "logical": 4.7,
                "total": 19.4
              },
              "metrics": {
                "instruction_reasoning": 49.9,
                "appearance_consistency": 71.0,
                "visual_plausibility": 91.5
              }
            },
            {
              "id": "bagel-w-cot",
              "name": "BAGEL (w/ CoT)",
              "group": null,
              "multi_image": null,
              "source_order": 8,
              "accuracy": {
                "temporal": 11.8,
                "causal": 27.8,
                "spatial": 21.0,
                "logical": 1.2,
                "total": 15.8
              },
              "metrics": {
                "instruction_reasoning": 47.6,
                "appearance_consistency": 75.6,
                "visual_plausibility": 81.7
              }
            },
            {
              "id": "gemini-2-0-flash-exp",
              "name": "Gemini-2.0-Flash-exp",
              "group": null,
              "multi_image": null,
              "source_order": 9,
              "accuracy": {
                "temporal": 9.4,
                "causal": 16.7,
                "spatial": 23.0,
                "logical": 4.7,
                "total": 13.9
              },
              "metrics": {
                "instruction_reasoning": 48.9,
                "appearance_consistency": 68.2,
                "visual_plausibility": 82.7
              }
            },
            {
              "id": "seedream-4-0",
              "name": "Seedream-4.0",
              "group": null,
              "multi_image": null,
              "source_order": 10,
              "accuracy": {
                "temporal": 17.6,
                "causal": 13.3,
                "spatial": 11.0,
                "logical": 7.1,
                "total": 12.2
              },
              "metrics": {
                "instruction_reasoning": 58.9,
                "appearance_consistency": 67.4,
                "visual_plausibility": 91.2
              }
            },
            {
              "id": "gemini-2-0-flash-pre",
              "name": "Gemini-2.0-Flash-pre",
              "group": null,
              "multi_image": null,
              "source_order": 11,
              "accuracy": {
                "temporal": 11.8,
                "causal": 14.4,
                "spatial": 11.0,
                "logical": 2.4,
                "total": 10.0
              },
              "metrics": {
                "instruction_reasoning": 49.9,
                "appearance_consistency": 68.4,
                "visual_plausibility": 84.9
              }
            },
            {
              "id": "qwen-image-edit-2509",
              "name": "Qwen-Image-Edit-2509",
              "group": null,
              "multi_image": null,
              "source_order": 12,
              "accuracy": {
                "temporal": 4.7,
                "causal": 11.1,
                "spatial": 17.0,
                "logical": 2.4,
                "total": 9.2
              },
              "metrics": {
                "instruction_reasoning": 37.2,
                "appearance_consistency": 66.4,
                "visual_plausibility": 86.9
              }
            },
            {
              "id": "bagel",
              "name": "BAGEL",
              "group": null,
              "multi_image": null,
              "source_order": 13,
              "accuracy": {
                "temporal": 3.5,
                "causal": 4.4,
                "spatial": 14.0,
                "logical": 0.0,
                "total": 5.8
              },
              "metrics": {
                "instruction_reasoning": 36.4,
                "appearance_consistency": 58.7,
                "visual_plausibility": 72.0
              }
            },
            {
              "id": "flux-1-kontext-dev",
              "name": "FLUX.1-Kontext-Dev",
              "group": null,
              "multi_image": null,
              "source_order": 14,
              "accuracy": {
                "temporal": 2.3,
                "causal": 5.5,
                "spatial": 13.0,
                "logical": 1.2,
                "total": 5.8
              },
              "metrics": {
                "instruction_reasoning": 26.0,
                "appearance_consistency": 71.6,
                "visual_plausibility": 85.2
              }
            },
            {
              "id": "ovis-u1",
              "name": "Ovis-U1",
              "group": null,
              "multi_image": null,
              "source_order": 15,
              "accuracy": {
                "temporal": 1.1,
                "causal": 3.3,
                "spatial": 4.0,
                "logical": 2.4,
                "total": 2.8
              },
              "metrics": {
                "instruction_reasoning": 33.9,
                "appearance_consistency": 52.7,
                "visual_plausibility": 72.9
              }
            },
            {
              "id": "step1x-edit",
              "name": "Step1X-Edit",
              "group": null,
              "multi_image": null,
              "source_order": 16,
              "accuracy": {
                "temporal": 0.0,
                "causal": 2.2,
                "spatial": 2.0,
                "logical": 3.5,
                "total": 1.9
              },
              "metrics": {
                "instruction_reasoning": 25.1,
                "appearance_consistency": 41.5,
                "visual_plausibility": 73.5
              }
            },
            {
              "id": "omnigen",
              "name": "OmniGen",
              "group": null,
              "multi_image": null,
              "source_order": 17,
              "accuracy": {
                "temporal": 1.2,
                "causal": 1.1,
                "spatial": 0.0,
                "logical": 1.2,
                "total": 0.8
              },
              "metrics": {
                "instruction_reasoning": 22.0,
                "appearance_consistency": 32.6,
                "visual_plausibility": 55.3
              }
            },
            {
              "id": "emu2",
              "name": "EMU2",
              "group": null,
              "multi_image": null,
              "source_order": 18,
              "accuracy": {
                "temporal": 1.2,
                "causal": 1.1,
                "spatial": 0.0,
                "logical": 0.0,
                "total": 0.5
              },
              "metrics": {
                "instruction_reasoning": 22.6,
                "appearance_consistency": 38.2,
                "visual_plausibility": 78.3
              }
            },
            {
              "id": "hidream-edit",
              "name": "HiDream-Edit",
              "group": null,
              "multi_image": null,
              "source_order": 19,
              "accuracy": {
                "temporal": 0.0,
                "causal": 0.0,
                "spatial": 0.0,
                "logical": 0.0,
                "total": 0.0
              },
              "metrics": {
                "instruction_reasoning": 30.3,
                "appearance_consistency": 12.6,
                "visual_plausibility": 74.9
              }
            },
            {
              "id": "flux-1-canny",
              "name": "FLUX.1-Canny",
              "group": null,
              "multi_image": null,
              "source_order": 20,
              "accuracy": {
                "temporal": 0.0,
                "causal": 0.0,
                "spatial": 0.0,
                "logical": 0.0,
                "total": 0.0
              },
              "metrics": {
                "instruction_reasoning": 20.2,
                "appearance_consistency": 13.1,
                "visual_plausibility": 77.5
              }
            }
          ]
        }
      }
    }
  ]
}
