{
  "version": "v1",
  "generatedAt": "2026-05-19T17:58:04.809Z",
  "datasets": [
    {
      "id": "v1_Semi_Private",
      "displayName": "ARC-AGI-1",
      "url": ""
    }
  ],
  "evaluations": [
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "2025_human_panel",
      "modelDisplayName": "Human Panel",
      "modelType": null,
      "modelGroup": "Human",
      "modelReleaseDate": null,
      "providerId": "Human",
      "providerDisplayName": "Human",
      "providerColor": "#a9a9a9ff",
      "score": 0.98,
      "costPerTask": 17,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "ARChitects",
      "modelDisplayName": "ARChitects",
      "modelType": "Custom",
      "modelGroup": "Kaggle",
      "modelReleaseDate": "2024-11-03T00:00:00.000Z",
      "providerId": "ARC Prize 2024",
      "providerDisplayName": "ARC Prize 2024",
      "providerColor": "#ff841cff",
      "score": 0.56,
      "costPerTask": 0.2,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Claude 3.7",
      "modelDisplayName": "Claude 3.7",
      "modelType": "Base LLM",
      "modelGroup": null,
      "modelReleaseDate": "2025-02-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.136,
      "costPerTask": 0.058,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Claude 3.7 Thinking 16K",
      "modelDisplayName": "Claude 3.7 (16K)",
      "modelType": "CoT",
      "modelGroup": "Claude_3_7_thinking",
      "modelReleaseDate": "2025-02-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.286,
      "costPerTask": 0.33,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Claude 3.7 Thinking 1K",
      "modelDisplayName": "Claude 3.7 (1K)",
      "modelType": "CoT",
      "modelGroup": "Claude_3_7_thinking",
      "modelReleaseDate": "2025-02-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.116,
      "costPerTask": 0.07,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Claude 3.7 Thinking 8K",
      "modelDisplayName": "Claude 3.7 (8K)",
      "modelType": "CoT",
      "modelGroup": "Claude_3_7_thinking",
      "modelReleaseDate": "2025-02-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.212,
      "costPerTask": 0.21,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-4-5-2025-02-27",
      "modelDisplayName": "GPT-4.5",
      "modelType": "Base LLM",
      "modelGroup": null,
      "modelReleaseDate": "2025-02-27T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.103,
      "costPerTask": 0.29,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-4o-2024-11-20",
      "modelDisplayName": "GPT-4o",
      "modelType": "Base LLM",
      "modelGroup": null,
      "modelReleaseDate": "2024-11-20T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.045,
      "costPerTask": 0.05,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Icecuber",
      "modelDisplayName": "Icecuber",
      "modelType": "Custom",
      "modelGroup": "Kaggle",
      "modelReleaseDate": "2023-11-03T00:00:00.000Z",
      "providerId": "ARC Prize 2024",
      "providerDisplayName": "ARC Prize 2024",
      "providerColor": "#ff841cff",
      "score": 0.17,
      "costPerTask": 0.2,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "mturker",
      "modelDisplayName": "Avg. Mturker",
      "modelType": null,
      "modelGroup": "Human",
      "modelReleaseDate": null,
      "providerId": "Human",
      "providerDisplayName": "Human",
      "providerColor": "#a9a9a9ff",
      "score": 0.77,
      "costPerTask": 3,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-preview-low",
      "modelDisplayName": "o3 (Preview, Low) ¹",
      "modelType": "CoT + Synthesis",
      "modelGroup": "o3-preview",
      "modelReleaseDate": "2024-12-20T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.757,
      "costPerTask": 200,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "R1",
      "modelDisplayName": "Deepseek R1",
      "modelType": "CoT",
      "modelGroup": null,
      "modelReleaseDate": "2025-01-22T00:00:00.000Z",
      "providerId": "Deepseek",
      "providerDisplayName": "Deepseek",
      "providerColor": "#ffdc00ff",
      "score": 0.158,
      "costPerTask": 0.06,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "stem_grad",
      "modelDisplayName": "Stem Grad",
      "modelType": null,
      "modelGroup": "Human",
      "modelReleaseDate": null,
      "providerId": "Human",
      "providerDisplayName": "Human",
      "providerColor": "#a9a9a9ff",
      "score": 0.98,
      "costPerTask": 10,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Llama-4-Maverick-17B-128E-Instruct-FP8-together",
      "modelDisplayName": "Llama 4 Maverick",
      "modelType": "Base LLM",
      "modelGroup": "Llama 4",
      "modelReleaseDate": "2025-04-05T00:00:00.000Z",
      "providerId": "Meta",
      "providerDisplayName": "Meta",
      "providerColor": "#e43ba2ff",
      "score": 0.0438,
      "costPerTask": 0.0078,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "Llama-4-Scout-17B-16E-Instruct-together",
      "modelDisplayName": "Llama 4 Scout",
      "modelType": "Base LLM",
      "modelGroup": "Llama 4",
      "modelReleaseDate": "2025-04-05T00:00:00.000Z",
      "providerId": "Meta",
      "providerDisplayName": "Meta",
      "providerColor": "#e43ba2ff",
      "score": 0.005,
      "costPerTask": 0.0041,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-4-1-nano-2025-04-14",
      "modelDisplayName": "GPT-4.1-Nano",
      "modelType": "Base LLM",
      "modelGroup": "gpt-4.1",
      "modelReleaseDate": "2025-04-14T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0,
      "costPerTask": 0.0021,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-4-1-mini-2025-04-14",
      "modelDisplayName": "GPT-4.1-Mini",
      "modelType": "Base LLM",
      "modelGroup": "gpt-4.1",
      "modelReleaseDate": "2025-04-14T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.035,
      "costPerTask": 0.0078,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-4-1-2025-04-14",
      "modelDisplayName": "GPT-4.1",
      "modelType": "Base LLM",
      "modelGroup": "gpt-4.1",
      "modelReleaseDate": "2025-04-14T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.055,
      "costPerTask": 0.039,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o1-mini-2024-09-12",
      "modelDisplayName": "o1-mini",
      "modelType": "CoT",
      "modelGroup": "o1-mini",
      "modelReleaseDate": "2024-09-12T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.14,
      "costPerTask": 0.135,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-mini-2025-01-31-low",
      "modelDisplayName": "o3-mini (Low)",
      "modelType": "CoT",
      "modelGroup": "o3-mini",
      "modelReleaseDate": "2025-01-31T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.145,
      "costPerTask": 0.0519,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-mini-2025-01-31-medium",
      "modelDisplayName": "o3-mini (Medium)",
      "modelType": "CoT",
      "modelGroup": "o3-mini",
      "modelReleaseDate": "2025-01-31T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.2233,
      "costPerTask": 0.1907,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-mini-2025-01-31-high",
      "modelDisplayName": "o3-mini (High)",
      "modelType": "CoT",
      "modelGroup": "o3-mini",
      "modelReleaseDate": "2025-01-31T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.345,
      "costPerTask": 0.3989,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-2025-04-16-low",
      "modelDisplayName": "o3 (Low)",
      "modelType": "CoT",
      "modelGroup": "o3",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.415,
      "costPerTask": 0.1764,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-2025-04-16-medium",
      "modelDisplayName": "o3 (Medium)",
      "modelType": "CoT",
      "modelGroup": "o3",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5383,
      "costPerTask": 0.2882,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-2025-04-16-high",
      "modelDisplayName": "o3 (High)",
      "modelType": "CoT",
      "modelGroup": "o3",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.6083,
      "costPerTask": 0.5002,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o4-mini-2025-04-16-low",
      "modelDisplayName": "o4-mini (Low)",
      "modelType": "CoT",
      "modelGroup": "o4-mini",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.2133,
      "costPerTask": 0.0406,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o4-mini-2025-04-16-medium",
      "modelDisplayName": "o4-mini (Medium)",
      "modelType": "CoT",
      "modelGroup": "o4-mini",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.4183,
      "costPerTask": 0.15,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o4-mini-2025-04-16-high",
      "modelDisplayName": "o4-mini (High)",
      "modelType": "CoT",
      "modelGroup": "o4-mini",
      "modelReleaseDate": "2025-04-16T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5867,
      "costPerTask": 0.4058,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-flash-preview-05-20",
      "modelDisplayName": "Gemini 2.5 Flash (Preview)",
      "modelType": "CoT",
      "modelGroup": null,
      "modelReleaseDate": "2025-05-20T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.3333,
      "costPerTask": 0.0371,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-flash-preview-05-20-thinking-1k",
      "modelDisplayName": "Gemini 2.5 Flash (Preview) (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-flash-preview-05-20-thinking",
      "modelReleaseDate": "2025-05-20T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.16,
      "costPerTask": 0.0356,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-flash-preview-05-20-thinking-8k",
      "modelDisplayName": "Gemini 2.5 Flash (Preview) (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-flash-preview-05-20-thinking",
      "modelReleaseDate": "2025-05-20T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.2583,
      "costPerTask": 0.1344,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-flash-preview-05-20-thinking-16k",
      "modelDisplayName": "Gemini 2.5 Flash (Preview) (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-flash-preview-05-20-thinking",
      "modelReleaseDate": "2025-05-20T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.3333,
      "costPerTask": 0.2134,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-flash-preview-05-20-thinking-24k",
      "modelDisplayName": "Gemini 2.5 Flash (Preview) (Thinking 24K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-flash-preview-05-20-thinking",
      "modelReleaseDate": "2025-05-20T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.3233,
      "costPerTask": 0.1971,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "codex-mini-latest",
      "modelDisplayName": "Codex Mini (Latest)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-05-23T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.2733,
      "costPerTask": 0.1597,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-20250514",
      "modelDisplayName": "Claude Sonnet 4",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.2383,
      "costPerTask": 0.0806,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-20250514-thinking-1k",
      "modelDisplayName": "Claude Sonnet 4 (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.28,
      "costPerTask": 0.0937,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-20250514-thinking-8k-bedrock",
      "modelDisplayName": "Claude Sonnet 4 (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.29,
      "costPerTask": 0.1952,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-20250514-thinking-16k-bedrock",
      "modelDisplayName": "Claude Sonnet 4 (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.4,
      "costPerTask": 0.3658,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-20250514-thinking-16k",
      "modelDisplayName": "Claude Opus 4 (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.3567,
      "costPerTask": 1.2496,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-20250514-thinking-8k",
      "modelDisplayName": "Claude Opus 4 (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.3067,
      "costPerTask": 0.7408,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-20250514-thinking-1k",
      "modelDisplayName": "Claude Opus 4 (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-20250514-thinking",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.27,
      "costPerTask": 0.5021,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-20250514",
      "modelDisplayName": "Claude Opus 4",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-05-14T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.225,
      "costPerTask": 0.4036,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "deepseek_r1_0528-openrouter",
      "modelDisplayName": "Deepseek R1 (05/28)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-05-28T00:00:00.000Z",
      "providerId": "Deepseek",
      "providerDisplayName": "Deepseek",
      "providerColor": "#ffdc00ff",
      "score": 0.2121,
      "costPerTask": 0.0464,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "grok-3-openrouter",
      "modelDisplayName": "Grok 3",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-02-19T00:00:00.000Z",
      "providerId": "xAI",
      "providerDisplayName": "xAI",
      "providerColor": "#ff1ed9",
      "score": 0.055,
      "costPerTask": 0.0931,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "grok-3-mini-beta-low-openrouter",
      "modelDisplayName": "Grok 3 Mini (Low)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-02-19T00:00:00.000Z",
      "providerId": "xAI",
      "providerDisplayName": "xAI",
      "providerColor": "#ff1ed9",
      "score": 0.165,
      "costPerTask": 0.0099,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-preview-openrouter",
      "modelDisplayName": "Gemini 2.5 Pro (Preview)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-02-19T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.33,
      "costPerTask": 0.5694,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-preview-05-06-thinking-1k",
      "modelDisplayName": "Gemini 2.5 Pro (Preview, Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-02-19T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.3133,
      "costPerTask": 0.5866,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-pro-2025-06-10-low",
      "modelDisplayName": "o3-Pro (Low)",
      "modelType": "CoT + Synthesis",
      "modelGroup": "o3-pro",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.4433,
      "costPerTask": 1.6382,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-pro-2025-06-10-medium",
      "modelDisplayName": "o3-Pro (Medium)",
      "modelType": "CoT + Synthesis",
      "modelGroup": "o3-pro",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.57,
      "costPerTask": 3.1766,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "o3-pro-2025-06-10-high",
      "modelDisplayName": "o3-Pro (High)",
      "modelType": "CoT + Synthesis",
      "modelGroup": "o3-pro",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5933,
      "costPerTask": 4.16,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "magistral-small-2506",
      "modelDisplayName": "Magistral Small",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "Mistral",
      "providerDisplayName": "Mistral",
      "providerColor": "#ffffff",
      "score": 0.05,
      "costPerTask": 0.0399,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "magistral-medium-2506",
      "modelDisplayName": "Magistral Medium",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "Mistral",
      "providerDisplayName": "Mistral",
      "providerColor": "#ffffff",
      "score": 0.0591,
      "costPerTask": 0.1015,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "magistral-medium-2506-thinking",
      "modelDisplayName": "Magistral Medium (Thinking)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-06-10T00:00:00.000Z",
      "providerId": "Mistral",
      "providerDisplayName": "Mistral",
      "providerColor": "#ffffff",
      "score": 0.0612,
      "costPerTask": 0.0989,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-2025-06-17-thinking-1k",
      "modelDisplayName": "Gemini 2.5 Pro (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-pro-2025-06-17-thinking",
      "modelReleaseDate": "2025-06-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.16,
      "costPerTask": 0.0573,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-2025-06-17-thinking-8k",
      "modelDisplayName": "Gemini 2.5 Pro (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-pro-2025-06-17-thinking",
      "modelReleaseDate": "2025-06-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.295,
      "costPerTask": 0.2947,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-2025-06-17-thinking-16k",
      "modelDisplayName": "Gemini 2.5 Pro (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-pro-2025-06-17-thinking",
      "modelReleaseDate": "2025-06-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.41,
      "costPerTask": 0.4839,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-2-5-pro-2025-06-17-thinking-32k",
      "modelDisplayName": "Gemini 2.5 Pro (Thinking 32K)",
      "modelType": "CoT",
      "modelGroup": "gemini-2-5-pro-2025-06-17-thinking",
      "modelReleaseDate": "2025-06-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.37,
      "costPerTask": 0.5123,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "grok-4-0709",
      "modelDisplayName": "Grok 4 (Thinking)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-07-09T00:00:00.000Z",
      "providerId": "xAI",
      "providerDisplayName": "xAI",
      "providerColor": "#ff1ed9",
      "score": 0.6667,
      "costPerTask": 1.0136,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "qwen3-235b-a22b-instruct-2507",
      "modelDisplayName": "Qwen3-235b-a22b Instruct (25/07)",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-07-25T00:00:00.000Z",
      "providerId": "Alibaba",
      "providerDisplayName": "Alibaba",
      "providerColor": "#ffffff",
      "score": 0.11,
      "costPerTask": 0.0025,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2025-08-07-high",
      "modelDisplayName": "GPT-5 (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.6567,
      "costPerTask": 0.5087,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2025-08-07-medium",
      "modelDisplayName": "GPT-5 (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5617,
      "costPerTask": 0.3301,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2025-08-07-low",
      "modelDisplayName": "GPT-5 (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.44,
      "costPerTask": 0.1531,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2025-08-07-minimal",
      "modelDisplayName": "GPT-5 (Minimal)",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.06,
      "costPerTask": 0.0335,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-mini-2025-08-07-high",
      "modelDisplayName": "GPT-5 Mini (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-mini-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5433,
      "costPerTask": 0.116,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-mini-2025-08-07-medium",
      "modelDisplayName": "GPT-5 Mini (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-mini-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.3733,
      "costPerTask": 0.0401,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-mini-2025-08-07-low",
      "modelDisplayName": "GPT-5 Mini (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-mini-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.2633,
      "costPerTask": 0.0135,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-mini-2025-08-07-minimal",
      "modelDisplayName": "GPT-5 Mini (Minimal)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.0533,
      "costPerTask": 0.0057,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-nano-2025-08-07-high",
      "modelDisplayName": "GPT-5 Nano (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-nano-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.1667,
      "costPerTask": 0.0292,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-nano-2025-08-07-medium",
      "modelDisplayName": "GPT-5 Nano (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-nano-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.2071,
      "costPerTask": 0.0124,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-nano-2025-08-07-low",
      "modelDisplayName": "GPT-5 Nano (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-nano-reasoning",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.0404,
      "costPerTask": 0.0033,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-nano-2025-08-07-minimal",
      "modelDisplayName": "GPT-5 Nano (Minimal)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.015,
      "costPerTask": 0.0015,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "hrm-2-2508",
      "modelDisplayName": "Hierarchical Reasoning Model (HRM)",
      "modelType": "",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "bespoke",
      "providerDisplayName": "Bespoke",
      "providerColor": "#ff841cff",
      "score": 0.32,
      "costPerTask": 1.48,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "jeremy_sept_2025",
      "modelDisplayName": "Grok 4 (Refine.)",
      "modelType": "Refinement",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "j_berman",
      "providerDisplayName": "J. Berman",
      "providerColor": "#ffffff",
      "score": 0.796,
      "costPerTask": 8.42,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "eric_pang_sept_2025",
      "modelDisplayName": "Grok 4 (Refine.)",
      "modelType": "Refinement",
      "modelGroup": "",
      "modelReleaseDate": "2025-08-07T00:00:00.000Z",
      "providerId": "e_pang",
      "providerDisplayName": "E. Pang",
      "providerColor": "#ffffff",
      "score": 0.771,
      "costPerTask": 2.56,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-5-20250929",
      "modelDisplayName": "Claude Sonnet 4.5",
      "modelType": "Base LLM",
      "modelGroup": "claude-sonnet-4-5-20250929",
      "modelReleaseDate": "2025-09-29T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.255,
      "costPerTask": 0.0808,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-5-20250929-thinking-1k",
      "modelDisplayName": "Claude Sonnet 4.5 (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-5-20250929",
      "modelReleaseDate": "2025-09-29T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.31,
      "costPerTask": 0.0928,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-5-20250929-thinking-8k",
      "modelDisplayName": "Claude Sonnet 4.5 (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-5-20250929",
      "modelReleaseDate": "2025-09-29T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.465,
      "costPerTask": 0.1776,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-5-20250929-thinking-16k",
      "modelDisplayName": "Claude Sonnet 4.5 (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-5-20250929",
      "modelReleaseDate": "2025-09-29T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.4833,
      "costPerTask": 0.2683,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-sonnet-4-5-20250929-thinking-32k",
      "modelDisplayName": "Claude Sonnet 4.5 (Thinking 32K)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-5-20250929",
      "modelReleaseDate": "2025-09-29T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.6367,
      "costPerTask": 0.5193,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-pro-2025-10-06",
      "modelDisplayName": "GPT-5 Pro",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2025-10-06T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.7017,
      "costPerTask": 4.7785,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "trm-2025-10-07",
      "modelDisplayName": "Tiny Recursion Model (TRM)",
      "modelType": "",
      "modelGroup": "",
      "modelReleaseDate": "2025-10-07T00:00:00.000Z",
      "providerId": "bespoke",
      "providerDisplayName": "Bespoke",
      "providerColor": "#ff841cff",
      "score": 0.4,
      "costPerTask": 1.7638,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-haiku-4-5-20251001",
      "modelDisplayName": "Claude Haiku 4.5",
      "modelType": "Base LLM",
      "modelGroup": "claude-haiku-4-5-20251001",
      "modelReleaseDate": "2025-10-01T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.1433,
      "costPerTask": 0.0263,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-haiku-4-5-20251001-thinking-1k",
      "modelDisplayName": "Claude Haiku 4.5 (Thinking 1K)",
      "modelType": "CoT",
      "modelGroup": "claude-haiku-4-5-20251001",
      "modelReleaseDate": "2025-10-01T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.1683,
      "costPerTask": 0.0306,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-haiku-4-5-20251001-thinking-8k",
      "modelDisplayName": "Claude Haiku 4.5 (Thinking 8K)",
      "modelType": "CoT",
      "modelGroup": "claude-haiku-4-5-20251001",
      "modelReleaseDate": "2025-10-01T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.255,
      "costPerTask": 0.0687,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-haiku-4-5-20251001-thinking-16k",
      "modelDisplayName": "Claude Haiku 4.5 (Thinking 16K)",
      "modelType": "CoT",
      "modelGroup": "claude-haiku-4-5-20251001",
      "modelReleaseDate": "2025-10-01T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.3733,
      "costPerTask": 0.1042,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-haiku-4-5-20251001-thinking-32k",
      "modelDisplayName": "Claude Haiku 4.5 (Thinking 32K)",
      "modelType": "CoT",
      "modelGroup": "claude-haiku-4-5-20251001",
      "modelReleaseDate": "2025-10-01T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.4767,
      "costPerTask": 0.2558,
      "resultsUrl": "",
      "display": true,
      "displayLabel": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "grok-4-fast-reasoning",
      "modelDisplayName": "Grok 4 (Fast Reasoning)",
      "modelType": "CoT",
      "modelGroup": "grok-4-0709",
      "modelReleaseDate": "2025-10-21T00:00:00.000Z",
      "providerId": "xAI",
      "providerDisplayName": "xAI",
      "providerColor": "#ff1ed9",
      "score": 0.485,
      "costPerTask": 0.0307,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-1-2025-11-13-thinking-none",
      "modelDisplayName": "GPT-5.1 (Thinking, None)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-1-reasoning",
      "modelReleaseDate": "2025-11-13T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.0583,
      "costPerTask": 0.0338,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-1-2025-11-13-thinking-low",
      "modelDisplayName": "GPT-5.1 (Thinking, Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-1-reasoning",
      "modelReleaseDate": "2025-11-13T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.3317,
      "costPerTask": 0.1,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-1-2025-11-13-thinking-medium",
      "modelDisplayName": "GPT-5.1 (Thinking, Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-1-reasoning",
      "modelReleaseDate": "2025-11-13T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5767,
      "costPerTask": 0.3149,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-1-2025-11-13-thinking-high",
      "modelDisplayName": "GPT-5.1 (Thinking, High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-1-reasoning",
      "modelReleaseDate": "2025-11-13T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.7283,
      "costPerTask": 0.674,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-pro-preview",
      "modelDisplayName": "Gemini 3 Pro",
      "modelType": "CoT",
      "modelGroup": "gemini-3-pro",
      "modelReleaseDate": "2025-11-18T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.75,
      "costPerTask": 0.4926,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-deep-think-preview",
      "modelDisplayName": "Gemini 3 Deep Think (Preview) ²",
      "modelType": "CoT",
      "modelGroup": "gemini-3-deep-think-preview",
      "modelReleaseDate": "2026-02-12T16:13:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.875,
      "costPerTask": 44.25900135,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-none",
      "modelDisplayName": "Opus 4.5 (Thinking, None)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.4,
      "costPerTask": 0.13,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-1k",
      "modelDisplayName": "Opus 4.5 (Thinking, 1K)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.3517,
      "costPerTask": 0.15,
      "resultsUrl": "",
      "display": false
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-8k",
      "modelDisplayName": "Opus 4.5 (Thinking, 8K)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.5867,
      "costPerTask": 0.38,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-16k",
      "modelDisplayName": "Opus 4.5 (Thinking, 16K)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.72,
      "costPerTask": 0.62,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-32k",
      "modelDisplayName": "Opus 4.5 (Thinking, 32K)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.7583,
      "costPerTask": 0.95,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-5-20251101-thinking-64k",
      "modelDisplayName": "Opus 4.5 (Thinking, 64K)",
      "modelType": "CoT",
      "modelGroup": "opus-4-5-thinking",
      "modelReleaseDate": "2025-11-24T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.8,
      "costPerTask": 1.47,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-2025-12-11-thinking-none",
      "modelDisplayName": "GPT-5.2",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.1233,
      "costPerTask": 0.0472,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-2025-12-11-thinking-low",
      "modelDisplayName": "GPT-5.2 (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.5567,
      "costPerTask": 0.1657,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-2025-12-11-thinking-medium",
      "modelDisplayName": "GPT-5.2 (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.7267,
      "costPerTask": 0.3448,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-2025-12-11-thinking-high",
      "modelDisplayName": "GPT-5.2 (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.7867,
      "costPerTask": 0.5196,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-2025-12-11-thinking-xhigh",
      "modelDisplayName": "GPT-5.2 (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.8617,
      "costPerTask": 0.96,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-pro-2025-12-11-medium",
      "modelDisplayName": "GPT-5.2 Pro (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-pro-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.8117,
      "costPerTask": 3.9774,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-pro-2025-12-11-high",
      "modelDisplayName": "GPT-5.2 Pro (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-pro-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.8567,
      "costPerTask": 5.8694,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-2-pro-2025-12-11-xhigh",
      "modelDisplayName": "GPT-5.2 Pro (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-2-pro-2025-12-11-thinking",
      "modelReleaseDate": "2025-12-11T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.905,
      "costPerTask": 11.6542,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-flash-preview-thinking-minimal",
      "modelDisplayName": "Gemini 3 Flash Preview (Minimal)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-flash-preview-thinking",
      "modelReleaseDate": "2025-12-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.215,
      "costPerTask": 0.012,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-flash-preview-thinking-low",
      "modelDisplayName": "Gemini 3 Flash Preview (Low)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-flash-preview-thinking",
      "modelReleaseDate": "2025-12-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.29,
      "costPerTask": 0.0163,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-flash-preview-thinking-medium",
      "modelDisplayName": "Gemini 3 Flash Preview (Medium)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-flash-preview-thinking",
      "modelReleaseDate": "2025-12-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.5767,
      "costPerTask": 0.0612,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-flash-preview-thinking-high",
      "modelDisplayName": "Gemini 3 Flash Preview (High)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-flash-preview-thinking",
      "modelReleaseDate": "2025-12-17T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.8467,
      "costPerTask": 0.1743,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "grok-4.20-beta-0309b-reasoning",
      "modelDisplayName": "Grok 4.20 (Reasoning)",
      "modelType": "CoT",
      "modelGroup": "grok-4.20-beta-0309b-reasoning",
      "modelReleaseDate": "2026-03-09T00:00:00.000Z",
      "providerId": "xAI",
      "providerDisplayName": "xAI",
      "providerColor": "#ff1ed9",
      "score": 0.895,
      "costPerTask": 0.35,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "johan_land_gpt_5_2_refine",
      "modelDisplayName": "GPT-5.2 (Refine.)",
      "modelType": "Refinement",
      "modelGroup": "",
      "modelReleaseDate": "2026-02-03T00:00:00.000Z",
      "providerId": "johan_land",
      "providerDisplayName": "Johan Land",
      "providerColor": "#ffffff",
      "score": 0.945,
      "costPerTask": 11.4,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-6-thinking-120K-low",
      "modelDisplayName": "Claude Opus 4.6 (120K, Low)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-6-thinking",
      "modelReleaseDate": "2026-02-05T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.86,
      "costPerTask": 0.648,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-6-thinking-120K-medium",
      "modelDisplayName": "Claude Opus 4.6 (120K, Medium)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-6-thinking",
      "modelReleaseDate": "2026-02-05T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.92,
      "costPerTask": 0.9647,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-6-thinking-120K-high",
      "modelDisplayName": "Claude Opus 4.6 (120K, High)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-6-thinking",
      "modelReleaseDate": "2026-02-05T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.94,
      "costPerTask": 1.3948,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-opus-4-6-thinking-120K-max",
      "modelDisplayName": "Claude Opus 4.6 (120K, Max)",
      "modelType": "CoT",
      "modelGroup": "claude-opus-4-6-thinking",
      "modelReleaseDate": "2026-02-05T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.93,
      "costPerTask": 1.8791,
      "resultsUrl": "",
      "display": true,
      "labelOffsetX": -17,
      "labelOffsetY": -13
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini_3_deep_think_022026",
      "modelDisplayName": "Gemini 3 Deep Think (2/26)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2026-02-12T16:13:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.96,
      "costPerTask": 7.171,
      "resultsUrl": "",
      "display": true,
      "labelOffsetX": -2,
      "labelOffsetY": -8
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude_sonnet_4_6_max",
      "modelDisplayName": "Claude Sonnet 4.6 (Max)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-6",
      "modelReleaseDate": "2026-02-17T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.86,
      "costPerTask": 1.452,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude_sonnet_4_6_high",
      "modelDisplayName": "Claude Sonnet 4.6 (High)",
      "modelType": "CoT",
      "modelGroup": "claude-sonnet-4-6",
      "modelReleaseDate": "2026-02-17T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.865,
      "costPerTask": 1.1908,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-1-pro-preview",
      "modelDisplayName": "Gemini 3.1 Pro (Preview)",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2026-02-19T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.98,
      "costPerTask": 0.5223,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "kimi-k2.5",
      "modelDisplayName": "Kimi K2.5",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2026-01-27T00:00:00.000Z",
      "providerId": "Moonshot AI",
      "providerDisplayName": "Moonshot AI",
      "providerColor": "#00c8ff",
      "score": 0.6533,
      "costPerTask": 0.15,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "minimax-m2.5",
      "modelDisplayName": "Minimax M2.5",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2026-02-12T00:00:00.000Z",
      "providerId": "Minimax",
      "providerDisplayName": "Minimax",
      "providerColor": "#ffffff",
      "score": 0.6367,
      "costPerTask": 0.07,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "deepseek-v3.2",
      "modelDisplayName": "Deepseek V3.2",
      "modelType": "Base LLM",
      "modelGroup": "",
      "modelReleaseDate": "2025-12-01T00:00:00.000Z",
      "providerId": "Deepseek",
      "providerDisplayName": "Deepseek",
      "providerColor": "#ffdc00ff",
      "score": 0.57,
      "costPerTask": 0.08,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "glm-5",
      "modelDisplayName": "GLM-5",
      "modelType": "CoT",
      "modelGroup": "",
      "modelReleaseDate": "2026-02-20T00:00:00.000Z",
      "providerId": "Z.ai",
      "providerDisplayName": "Z.ai",
      "providerColor": "#ffffff",
      "score": 0.4467,
      "costPerTask": 0.17,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-low",
      "modelDisplayName": "GPT-5.4 (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4",
      "modelReleaseDate": "2026-03-04T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.6817,
      "costPerTask": 0.15,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-medium",
      "modelDisplayName": "GPT-5.4 (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4",
      "modelReleaseDate": "2026-03-04T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.8617,
      "costPerTask": 0.25,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-high",
      "modelDisplayName": "GPT-5.4 (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4",
      "modelReleaseDate": "2026-03-04T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.9267,
      "costPerTask": 0.37,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-xhigh",
      "modelDisplayName": "GPT-5.4 (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4",
      "modelReleaseDate": "2026-03-04T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.9367,
      "costPerTask": 0.62,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-pro-xhigh",
      "modelDisplayName": "GPT-5.4 Pro (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-pro",
      "modelReleaseDate": "2026-03-04T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.945,
      "costPerTask": 7.21,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-mini-xhigh",
      "modelDisplayName": "GPT-5.4 Mini (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-mini-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.6367,
      "costPerTask": 0.51,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-mini-high",
      "modelDisplayName": "GPT-5.4 Mini (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-mini-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.58,
      "costPerTask": 0.27,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-mini-medium",
      "modelDisplayName": "GPT-5.4 Mini (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-mini-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.4083,
      "costPerTask": 0.16,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-mini-low",
      "modelDisplayName": "GPT-5.4 Mini (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-mini-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.13,
      "costPerTask": 0.04,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-nano-xhigh",
      "modelDisplayName": "GPT-5.4 Nano (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-nano-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.515,
      "costPerTask": 0.13,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-nano-high",
      "modelDisplayName": "GPT-5.4 Nano (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-nano-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.3817,
      "costPerTask": 0.07,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-nano-medium",
      "modelDisplayName": "GPT-5.4 Nano (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-nano-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.33,
      "costPerTask": 0.04,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-4-nano-low",
      "modelDisplayName": "GPT-5.4 Nano (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-4-nano-reasoning",
      "modelReleaseDate": "2026-03-17T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.1833,
      "costPerTask": 0.01,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-4-7-low",
      "modelDisplayName": "Claude 4.7 (Low)",
      "modelType": "CoT",
      "modelGroup": "claude-4-7",
      "modelReleaseDate": "2026-04-16T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.91,
      "costPerTask": 0.76,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-4-7-medium",
      "modelDisplayName": "Claude 4.7 (Medium)",
      "modelType": "CoT",
      "modelGroup": "claude-4-7",
      "modelReleaseDate": "2026-04-16T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.91,
      "costPerTask": 1.04,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-4-7-high",
      "modelDisplayName": "Claude 4.7 (High)",
      "modelType": "CoT",
      "modelGroup": "claude-4-7",
      "modelReleaseDate": "2026-04-16T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.935,
      "costPerTask": 1.41,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "claude-4-7-max",
      "modelDisplayName": "Claude 4.7 (Max)",
      "modelType": "CoT",
      "modelGroup": "claude-4-7",
      "modelReleaseDate": "2026-04-16T00:00:00.000Z",
      "providerId": "Anthropic",
      "providerDisplayName": "Anthropic",
      "providerColor": "#f93c32ff",
      "score": 0.92,
      "costPerTask": 2.58,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-2026-04-22-thinking-low",
      "modelDisplayName": "GPT-5.5 (Low)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-2026-04-22-thinking",
      "modelReleaseDate": "2026-04-22T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.7617,
      "costPerTask": 0.2,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-2026-04-22-thinking-medium",
      "modelDisplayName": "GPT-5.5 (Medium)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-2026-04-22-thinking",
      "modelReleaseDate": "2026-04-22T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.9217,
      "costPerTask": 0.39,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-2026-04-22-thinking-high",
      "modelDisplayName": "GPT-5.5 (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-2026-04-22-thinking",
      "modelReleaseDate": "2026-04-22T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.945,
      "costPerTask": 0.56,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-2026-04-22-thinking-xhigh",
      "modelDisplayName": "GPT-5.5 (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-2026-04-22-thinking",
      "modelReleaseDate": "2026-04-22T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.95,
      "costPerTask": 0.73,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-pro-2026-04-23-high",
      "modelDisplayName": "GPT-5.5 Pro (High)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-pro-2026-04-23-thinking",
      "modelReleaseDate": "2026-04-23T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.965,
      "costPerTask": 4.53,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gpt-5-5-pro-2026-04-23-xhigh",
      "modelDisplayName": "GPT-5.5 Pro (xHigh)",
      "modelType": "CoT",
      "modelGroup": "gpt-5-5-pro-2026-04-23-thinking",
      "modelReleaseDate": "2026-04-23T00:00:00.000Z",
      "providerId": "OpenAI",
      "providerDisplayName": "OpenAI",
      "providerColor": "#1e93ffff",
      "score": 0.95,
      "costPerTask": 4.52,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-5-flash-minimal",
      "modelDisplayName": "Gemini 3.5 Flash (Minimal)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-5-flash",
      "modelReleaseDate": "2026-05-19T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.4883,
      "costPerTask": 0.0645,
      "resultsUrl": "",
      "display": true
    },
    {
      "datasetId": "v1_Semi_Private",
      "datasetDisplayName": "ARC-AGI-1",
      "modelId": "gemini-3-5-flash-high",
      "modelDisplayName": "Gemini 3.5 Flash (High)",
      "modelType": "CoT",
      "modelGroup": "gemini-3-5-flash",
      "modelReleaseDate": "2026-05-19T00:00:00.000Z",
      "providerId": "Google",
      "providerDisplayName": "Google",
      "providerColor": "#4ecc30ff",
      "score": 0.925,
      "costPerTask": 0.4278,
      "resultsUrl": "",
      "display": true
    }
  ]
}
