{
  "generatedAt": "2026-05-28T12:03:41.683Z",
  "source": "openevals",
  "title": "OpenEvals leaderboard-data",
  "dataset": "OpenEvals/leaderboard-data",
  "config": "default",
  "split": "train",
  "totalRows": 105,
  "fetchedRows": 105,
  "partial": false,
  "partialReason": null,
  "scoreKeys": [
    "aime2026_score",
    "evasionBench_score",
    "gpqa_score",
    "gsm8k_score",
    "hle_score",
    "hmmt2026_score",
    "mmluPro_score",
    "olmOcr_score",
    "swePro_score",
    "sweVerified_score",
    "terminalBench_score",
    "aggregate_score"
  ],
  "topModels": [
    {
      "modelId": "meta-llama-llama-3.1-405b",
      "modelName": "meta-llama/Llama-3.1-405B",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 405.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 96.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 96.8,
        "aggregate_score": 96.8
      }
    },
    {
      "modelId": "microsoft-phi-3-medium-4k-instruct",
      "modelName": "microsoft/Phi-3-medium-4k-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 14,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 91,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 91,
        "aggregate_score": 91
      }
    },
    {
      "modelId": "qwen-qwen2-72b",
      "modelName": "Qwen/Qwen2-72B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 72.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 89.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 89.5,
        "aggregate_score": 89.5
      }
    },
    {
      "modelId": "microsoft-phi-3.5-mini-instruct",
      "modelName": "microsoft/Phi-3.5-mini-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 3.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 86.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 86.2,
        "aggregate_score": 86.2
      }
    },
    {
      "modelId": "internlm-internlm2_5-7b-chat",
      "modelName": "internlm/internlm2_5-7b-chat",
      "provider": "internlm",
      "modelType": "open",
      "parametersBillions": 7.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 86,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 86,
        "aggregate_score": 86
      }
    },
    {
      "modelId": "datalab-to-chandra-ocr-2",
      "modelName": "datalab-to/chandra-ocr-2",
      "provider": "datalab-to",
      "modelType": "open",
      "parametersBillions": 5.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 85.9,
        "aggregate_score": 85.9
      }
    },
    {
      "modelId": "microsoft-phi-3-mini-4k-instruct",
      "modelName": "microsoft/Phi-3-mini-4k-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 3.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85.7,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 85.7,
        "aggregate_score": 85.7
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-r1-0528",
      "modelName": "deepseek-ai/DeepSeek-R1-0528",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 85,
        "aggregate_score": 85
      }
    },
    {
      "modelId": "qwen-qwen3-235b-a22b-thinking-2507",
      "modelName": "Qwen/Qwen3-235B-A22B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 84.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 84.4,
        "aggregate_score": 84.4
      }
    },
    {
      "modelId": "rednote-hilab-dots.mocr",
      "modelName": "rednote-hilab/dots.mocr",
      "provider": "rednote-hilab",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-4bit",
      "modelName": "mlx-community/dots.mocr-4bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-5bit",
      "modelName": "mlx-community/dots.mocr-5bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-6bit",
      "modelName": "mlx-community/dots.mocr-6bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-8bit",
      "modelName": "mlx-community/dots.mocr-8bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-bf16",
      "modelName": "mlx-community/dots.mocr-bf16",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-mxfp4",
      "modelName": "mlx-community/dots.mocr-mxfp4",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-mxfp8",
      "modelName": "mlx-community/dots.mocr-mxfp8",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-nvfp4",
      "modelName": "mlx-community/dots.mocr-nvfp4",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "lightonai-lightonocr-2-1b",
      "modelName": "lightonai/LightOnOCR-2-1B",
      "provider": "lightonai",
      "modelType": "open",
      "parametersBillions": 1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.2,
        "aggregate_score": 83.2
      }
    },
    {
      "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
      "modelName": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 30.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.15,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "aime2026_score": 87.5,
        "hmmt2026_score": 78.79,
        "aggregate_score": 83.15
      }
    },
    {
      "modelId": "datalab-to-chandra",
      "modelName": "datalab-to/chandra",
      "provider": "datalab-to",
      "modelType": "open",
      "parametersBillions": 8.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.1,
        "aggregate_score": 83.1
      }
    },
    {
      "modelId": "infly-infinity-parser-7b",
      "modelName": "infly/Infinity-Parser-7B",
      "provider": "infly",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.5,
        "aggregate_score": 82.5
      }
    },
    {
      "modelId": "allenai-olmocr-2-7b-1025-fp8",
      "modelName": "allenai/olmOCR-2-7B-1025-FP8",
      "provider": "allenai",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.4,
        "aggregate_score": 82.4
      }
    },
    {
      "modelId": "titanml-olmocr-2-7b-1025-fp8",
      "modelName": "TitanML/olmOCR-2-7B-1025-FP8",
      "provider": "TitanML",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.4,
        "aggregate_score": 82.4
      }
    },
    {
      "modelId": "qwen-qwen3.5-9b",
      "modelName": "Qwen/Qwen3.5-9B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 9.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 81.98,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "aime2026_score": 92.5,
        "gpqa_score": 81.7,
        "hmmt2026_score": 71.21,
        "mmluPro_score": 82.5,
        "aggregate_score": 81.98
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3-0324",
      "modelName": "deepseek-ai/DeepSeek-V3-0324",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 81.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 81.2,
        "aggregate_score": 81.2
      }
    },
    {
      "modelId": "qwen-qwen3-next-80b-a3b-instruct",
      "modelName": "Qwen/Qwen3-Next-80B-A3B-Instruct",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 81.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 80.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 80.6,
        "aggregate_score": 80.6
      }
    },
    {
      "modelId": "paddlepaddle-paddleocr-vl",
      "modelName": "PaddlePaddle/PaddleOCR-VL",
      "provider": "PaddlePaddle",
      "modelType": "open",
      "parametersBillions": 1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 80,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 80,
        "aggregate_score": 80
      }
    },
    {
      "modelId": "qwen-qwen2-7b",
      "modelName": "Qwen/Qwen2-7B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 7.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.9,
        "aggregate_score": 79.9
      }
    },
    {
      "modelId": "baidu-qianfan-ocr",
      "modelName": "baidu/Qianfan-OCR",
      "provider": "baidu",
      "modelType": "open",
      "parametersBillions": 4.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 79.8,
        "aggregate_score": 79.8
      }
    },
    {
      "modelId": "internlm-internlm2-chat-20b",
      "modelName": "internlm/internlm2-chat-20b",
      "provider": "internlm",
      "modelType": "open",
      "parametersBillions": 19.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.6,
        "aggregate_score": 79.6
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v2",
      "modelName": "deepseek-ai/DeepSeek-V2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 235.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.2,
        "aggregate_score": 79.2
      }
    },
    {
      "modelId": "rednote-hilab-dots.ocr",
      "modelName": "rednote-hilab/dots.ocr",
      "provider": "rednote-hilab",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 79.1,
        "aggregate_score": 79.1
      }
    },
    {
      "modelId": "meituan-longcat-longcat-flash-lite",
      "modelName": "meituan-longcat/LongCat-Flash-Lite",
      "provider": "meituan-longcat",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 78.29,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 78.29,
        "aggregate_score": 78.29
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-r1",
      "modelName": "deepseek-ai/DeepSeek-R1",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.75,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 71.5,
        "mmluPro_score": 84,
        "aggregate_score": 77.75
      }
    },
    {
      "modelId": "jdopensource-joyai-llm-flash",
      "modelName": "jdopensource/JoyAI-LLM-Flash",
      "provider": "jdopensource",
      "modelType": "open",
      "parametersBillions": 49.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.72,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 74.43,
        "mmluPro_score": 81.02,
        "aggregate_score": 77.72
      }
    },
    {
      "modelId": "qwen-qwen3.5-4b",
      "modelName": "Qwen/Qwen3.5-4B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.65,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 76.2,
        "mmluPro_score": 79.1,
        "aggregate_score": 77.65
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3",
      "modelName": "deepseek-ai/DeepSeek-V3",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.85,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gsm8k_score": 89.3,
        "mmluPro_score": 64.4,
        "aggregate_score": 76.85
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-ocr-2",
      "modelName": "deepseek-ai/DeepSeek-OCR-2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 3.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.3,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 76.3,
        "aggregate_score": 76.3
      }
    },
    {
      "modelId": "lightonai-lightonocr-1b-1025",
      "modelName": "lightonai/LightOnOCR-1B-1025",
      "provider": "lightonai",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 76.1,
        "aggregate_score": 76.1
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-ocr",
      "modelName": "deepseek-ai/DeepSeek-OCR",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 3.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.7,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.7,
        "aggregate_score": 75.7
      }
    },
    {
      "modelId": "arcee-ai-trinity-large-preview",
      "modelName": "arcee-ai/Trinity-Large-Preview",
      "provider": "arcee-ai",
      "modelType": "open",
      "parametersBillions": 398.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "ares-realm-studios-trinity-large-preview-arstest",
      "modelName": "Ares-Realm-Studios/Trinity-Large-Preview-ARSTEST",
      "provider": "Ares-Realm-Studios",
      "modelType": "open",
      "parametersBillions": 398.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "opendatalab-mineru2.5-2509-1.2b",
      "modelName": "opendatalab/MinerU2.5-2509-1.2B",
      "provider": "opendatalab",
      "modelType": "open",
      "parametersBillions": 1.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "zai-org-glm-ocr",
      "modelName": "zai-org/GLM-OCR",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "multilingual-multimodal-nlp-industrialcoder",
      "modelName": "Multilingual-Multimodal-NLP/IndustrialCoder",
      "provider": "Multilingual-Multimodal-NLP",
      "modelType": "open",
      "parametersBillions": 32,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 74.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 74.8,
        "aggregate_score": 74.8
      }
    },
    {
      "modelId": "qwen-qwen3.5-397b-a17b",
      "modelName": "Qwen/Qwen3.5-397B-A17B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 403.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 73.57,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 93.33,
        "gpqa_score": 88.4,
        "hle_score": 28.7,
        "hmmt2026_score": 87.88,
        "mmluPro_score": 87.8,
        "sweVerified_score": 76.4,
        "terminalBench_score": 52.5,
        "aggregate_score": 73.57
      }
    },
    {
      "modelId": "lm-provers-qed-nano",
      "modelName": "lm-provers/QED-Nano",
      "provider": "lm-provers",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 72.69,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "aime2026_score": 82.5,
        "hmmt2026_score": 62.88,
        "aggregate_score": 72.69
      }
    },
    {
      "modelId": "moonshotai-kimi-k2.5",
      "modelName": "moonshotai/Kimi-K2.5",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1058.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.57,
      "coverageCount": 8,
      "coveragePercent": 72.7,
      "scores": {
        "aime2026_score": 95.83,
        "gpqa_score": 87.6,
        "hle_score": 50.2,
        "hmmt2026_score": 87.12,
        "mmluPro_score": 87.1,
        "swePro_score": 50.7,
        "sweVerified_score": 70.8,
        "terminalBench_score": 43.2,
        "aggregate_score": 71.57
      }
    },
    {
      "modelId": "stepfun-ai-step-3.5-flash",
      "modelName": "stepfun-ai/Step-3.5-Flash",
      "provider": "stepfun-ai",
      "modelType": "open",
      "parametersBillions": 199.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.35,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 96.67,
        "gpqa_score": 83.5,
        "hle_score": 23.1,
        "hmmt2026_score": 86.36,
        "mmluPro_score": 84.4,
        "sweVerified_score": 74.4,
        "terminalBench_score": 51,
        "aggregate_score": 71.35
      }
    },
    {
      "modelId": "mistralai-mistral-small-4-119b-2603",
      "modelName": "mistralai/Mistral-Small-4-119B-2603",
      "provider": "mistralai",
      "modelType": "open",
      "parametersBillions": 119.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gpqa_score": 71.2,
        "aggregate_score": 71.2
      }
    },
    {
      "modelId": "zai-org-glm-5",
      "modelName": "zai-org/GLM-5",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 753.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 70.65,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "aime2026_score": 95.83,
        "gpqa_score": 86,
        "hle_score": 30.5,
        "hmmt2026_score": 86.36,
        "sweVerified_score": 72.8,
        "terminalBench_score": 52.4,
        "aggregate_score": 70.65
      }
    },
    {
      "modelId": "fireredteam-firered-ocr",
      "modelName": "FireRedTeam/FireRed-OCR",
      "provider": "FireRedTeam",
      "modelType": "open",
      "parametersBillions": 2.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 70.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 70.2,
        "aggregate_score": 70.2
      }
    },
    {
      "modelId": "nanonets-nanonets-ocr2-3b",
      "modelName": "nanonets/Nanonets-OCR2-3B",
      "provider": "nanonets",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 69.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 69.5,
        "aggregate_score": 69.5
      }
    },
    {
      "modelId": "qwen-qwen3.5-27b",
      "modelName": "Qwen/Qwen3.5-27B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 27.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.83,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 90.83,
        "gpqa_score": 85.5,
        "hle_score": 24.3,
        "hmmt2026_score": 81.06,
        "mmluPro_score": 86.1,
        "sweVerified_score": 72.4,
        "terminalBench_score": 41.6,
        "aggregate_score": 68.83
      }
    },
    {
      "modelId": "qwen-qwen3-4b-thinking-2507",
      "modelName": "Qwen/Qwen3-4B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.83,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "aime2026_score": 82.5,
        "gpqa_score": 65.8,
        "hmmt2026_score": 53.03,
        "mmluPro_score": 74,
        "aggregate_score": 68.83
      }
    },
    {
      "modelId": "qwen-qwen3.5-35b-a3b",
      "modelName": "Qwen/Qwen3.5-35B-A3B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 36,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.11,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 93.33,
        "gpqa_score": 84.2,
        "hle_score": 22.4,
        "hmmt2026_score": 81.82,
        "mmluPro_score": 85.3,
        "sweVerified_score": 69.2,
        "terminalBench_score": 40.5,
        "aggregate_score": 68.11
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-instruct-0905",
      "modelName": "moonshotai/Kimi-K2-Instruct-0905",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1026.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 66.68,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "evasionBench_score": 66.68,
        "aggregate_score": 66.68
      }
    },
    {
      "modelId": "gair-openswe-72b",
      "modelName": "GAIR/OpenSWE-72B",
      "provider": "GAIR",
      "modelType": "open",
      "parametersBillions": 72.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 66,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 66,
        "aggregate_score": 66
      }
    },
    {
      "modelId": "qwen-qwen3-4b-instruct-2507",
      "modelName": "Qwen/Qwen3-4B-Instruct-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 65.8,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 62,
        "mmluPro_score": 69.6,
        "aggregate_score": 65.8
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3.2",
      "modelName": "deepseek-ai/DeepSeek-V3.2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 685.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64.28,
      "coverageCount": 9,
      "coveragePercent": 81.8,
      "scores": {
        "aime2026_score": 94.17,
        "evasionBench_score": 66.88,
        "gpqa_score": 82.4,
        "hle_score": 40.8,
        "hmmt2026_score": 84.09,
        "mmluPro_score": 85,
        "swePro_score": 15.56,
        "sweVerified_score": 70,
        "terminalBench_score": 39.6,
        "aggregate_score": 64.28
      }
    },
    {
      "modelId": "zai-org-glm-4.7",
      "modelName": "zai-org/GLM-4.7",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 358.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64.15,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "evasionBench_score": 82.91,
        "gpqa_score": 85.7,
        "hle_score": 24.8,
        "mmluPro_score": 84.3,
        "sweVerified_score": 73.8,
        "terminalBench_score": 33.4,
        "aggregate_score": 64.15
      }
    },
    {
      "modelId": "qwen-qwen3.5-122b-a10b",
      "modelName": "Qwen/Qwen3.5-122B-A10B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 125.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 86.6,
        "hle_score": 25.3,
        "mmluPro_score": 86.7,
        "sweVerified_score": 72,
        "terminalBench_score": 49.4,
        "aggregate_score": 64
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 123.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 62.97,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 90,
        "gpqa_score": 79.23,
        "hle_score": 18.26,
        "hmmt2026_score": 84.85,
        "mmluPro_score": 83.73,
        "sweVerified_score": 53.73,
        "terminalBench_score": 31,
        "aggregate_score": 62.97
      }
    },
    {
      "modelId": "gair-openswe-32b",
      "modelName": "GAIR/OpenSWE-32B",
      "provider": "GAIR",
      "modelType": "open",
      "parametersBillions": 32.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 62.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 62.4,
        "aggregate_score": 62.4
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-thinking",
      "modelName": "moonshotai/Kimi-K2-Thinking",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1058.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 60,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 84.5,
        "hle_score": 23.9,
        "mmluPro_score": 84.6,
        "sweVerified_score": 71.3,
        "terminalBench_score": 35.7,
        "aggregate_score": 60
      }
    },
    {
      "modelId": "minimaxai-minimax-m2.5",
      "modelName": "MiniMaxAI/MiniMax-M2.5",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 58.95,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "gpqa_score": 85.2,
        "hle_score": 19.4,
        "swePro_score": 55.4,
        "sweVerified_score": 75.8,
        "aggregate_score": 58.95
      }
    },
    {
      "modelId": "lgai-exaone-k-exaone-236b-a23b",
      "modelName": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "provider": "LGAI-EXAONE",
      "modelType": "open",
      "parametersBillions": 237.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 58.83,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 79.1,
        "hle_score": 13.6,
        "mmluPro_score": 83.8,
        "aggregate_score": 58.83
      }
    },
    {
      "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
      "modelName": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 57.87,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 76.1,
        "hle_score": 17.7,
        "mmluPro_score": 79.8,
        "aggregate_score": 57.87
      }
    },
    {
      "modelId": "qwen-qwen3.5-2b",
      "modelName": "Qwen/Qwen3.5-2B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 2.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 55.3,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 55.3,
        "aggregate_score": 55.3
      }
    },
    {
      "modelId": "meta-llama-llama-3.1-8b-instruct",
      "modelName": "meta-llama/Llama-3.1-8B-Instruct",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 54.4,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 30.4,
        "gsm8k_score": 84.5,
        "mmluPro_score": 48.3,
        "aggregate_score": 54.4
      }
    },
    {
      "modelId": "facebook-cwm",
      "modelName": "facebook/cwm",
      "provider": "facebook",
      "modelType": "open",
      "parametersBillions": 32.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 53.9,
        "aggregate_score": 53.9
      }
    },
    {
      "modelId": "minimaxai-minimax-m2.1",
      "modelName": "MiniMaxAI/MiniMax-M2.1",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.59,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "evasionBench_score": 71.31,
        "hle_score": 22.2,
        "mmluPro_score": 88,
        "swePro_score": 36.81,
        "sweVerified_score": 74,
        "terminalBench_score": 29.2,
        "aggregate_score": 53.59
      }
    },
    {
      "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
      "modelName": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "provider": "RedHatAI",
      "modelType": "open",
      "parametersBillions": 123.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.19,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 79.23,
        "hle_score": 18.26,
        "mmluPro_score": 83.73,
        "sweVerified_score": 53.73,
        "terminalBench_score": 31,
        "aggregate_score": 53.19
      }
    },
    {
      "modelId": "meituan-longcat-longcat-flash-thinking-2601",
      "modelName": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "provider": "meituan-longcat",
      "modelType": "open",
      "parametersBillions": 561.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 52.85,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 80.5,
        "hle_score": 25.2,
        "aggregate_score": 52.85
      }
    },
    {
      "modelId": "swe-lego-swe-lego-qwen3-32b",
      "modelName": "SWE-Lego/SWE-Lego-Qwen3-32B",
      "provider": "SWE-Lego",
      "modelType": "open",
      "parametersBillions": 0,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 52.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 52.6,
        "aggregate_score": 52.6
      }
    },
    {
      "modelId": "snurfyai-sn-logicer-0.8b",
      "modelName": "SnurfyAI/Sn-Logicer-0.8B",
      "provider": "SnurfyAI",
      "modelType": "open",
      "parametersBillions": 0.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 50.57,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 50.57,
        "aggregate_score": 50.57
      }
    },
    {
      "modelId": "qwen-qwen3-coder-next",
      "modelName": "Qwen/Qwen3-Coder-Next",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 79.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 50.37,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "swePro_score": 44.3,
        "sweVerified_score": 70.6,
        "terminalBench_score": 36.2,
        "aggregate_score": 50.37
      }
    },
    {
      "modelId": "zai-org-glm-4.7-flash",
      "modelName": "zai-org/GLM-4.7-Flash",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 31.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 49.6,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 75.2,
        "hle_score": 14.4,
        "sweVerified_score": 59.2,
        "aggregate_score": 49.6
      }
    },
    {
      "modelId": "minimaxai-minimax-m2",
      "modelName": "MiniMaxAI/MiniMax-M2",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 48.48,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "hle_score": 12.5,
        "mmluPro_score": 82,
        "sweVerified_score": 69.4,
        "terminalBench_score": 30,
        "aggregate_score": 48.48
      }
    },
    {
      "modelId": "nanbeige-nanbeige4.1-3b",
      "modelName": "Nanbeige/Nanbeige4.1-3B",
      "provider": "Nanbeige",
      "modelType": "open",
      "parametersBillions": 3.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 48.2,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 83.8,
        "hle_score": 12.6,
        "aggregate_score": 48.2
      }
    },
    {
      "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
      "modelName": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 480.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 46.92,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "evasionBench_score": 78.16,
        "swePro_score": 38.7,
        "terminalBench_score": 23.9,
        "aggregate_score": 46.92
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 46.9,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 15.5,
        "mmluPro_score": 78.3,
        "aggregate_score": 46.9
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 44.15,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 10.2,
        "mmluPro_score": 78.1,
        "aggregate_score": 44.15
      }
    },
    {
      "modelId": "swe-lego-swe-lego-qwen3-8b",
      "modelName": "SWE-Lego/SWE-Lego-Qwen3-8B",
      "provider": "SWE-Lego",
      "modelType": "open",
      "parametersBillions": 0,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 42.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 42.2,
        "aggregate_score": 42.2
      }
    },
    {
      "modelId": "tiiuae-falcon-h1r-7b",
      "modelName": "tiiuae/Falcon-H1R-7B",
      "provider": "tiiuae",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 41.6,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 11.1,
        "mmluPro_score": 72.1,
        "aggregate_score": 41.6
      }
    },
    {
      "modelId": "miromind-ai-mirothinker-v1.5-235b",
      "modelName": "miromind-ai/MiroThinker-v1.5-235B",
      "provider": "miromind-ai",
      "modelType": "open",
      "parametersBillions": 235.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 39.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 39.2,
        "aggregate_score": 39.2
      }
    },
    {
      "modelId": "liquidai-lfm2.5-1.2b-instruct",
      "modelName": "LiquidAI/LFM2.5-1.2B-Instruct",
      "provider": "LiquidAI",
      "modelType": "open",
      "parametersBillions": 1.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 38.89,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gpqa_score": 38.89,
        "aggregate_score": 38.89
      }
    },
    {
      "modelId": "nvidia-nemotron-orchestrator-8b",
      "modelName": "nvidia/Nemotron-Orchestrator-8B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 37.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 37.1,
        "aggregate_score": 37.1
      }
    },
    {
      "modelId": "openai-gpt-oss-120b",
      "modelName": "openai/gpt-oss-120b",
      "provider": "openai",
      "modelType": "open",
      "parametersBillions": 120.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 34.1,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "gpqa_score": 67.1,
        "hle_score": 5.2,
        "swePro_score": 16.2,
        "sweVerified_score": 47.9,
        "aggregate_score": 34.1
      }
    },
    {
      "modelId": "openai-gpt-oss-20b",
      "modelName": "openai/gpt-oss-20b",
      "provider": "openai",
      "modelType": "open",
      "parametersBillions": 21.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 32.8,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 56.8,
        "hle_score": 4.2,
        "sweVerified_score": 37.4,
        "aggregate_score": 32.8
      }
    },
    {
      "modelId": "miromind-ai-mirothinker-v1.5-30b",
      "modelName": "miromind-ai/MiroThinker-v1.5-30B",
      "provider": "miromind-ai",
      "modelType": "open",
      "parametersBillions": 30.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 31,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 31,
        "aggregate_score": 31
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-instruct",
      "modelName": "moonshotai/Kimi-K2-Instruct",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1026.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 27.73,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "swePro_score": 27.67,
        "terminalBench_score": 27.8,
        "aggregate_score": 27.73
      }
    },
    {
      "modelId": "nvidia-nemotron-terminal-32b",
      "modelName": "nvidia/Nemotron-Terminal-32B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 32.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 27.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "terminalBench_score": 27.4,
        "aggregate_score": 27.4
      }
    },
    {
      "modelId": "xiaomimimo-mimo-v2-flash",
      "modelName": "XiaomiMiMo/MiMo-V2-Flash",
      "provider": "XiaomiMiMo",
      "modelType": "open",
      "parametersBillions": 309.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 22.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 22.1,
        "aggregate_score": 22.1
      }
    },
    {
      "modelId": "qwen-qwen3-235b-a22b",
      "modelName": "Qwen/Qwen3-235B-A22B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 235.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 21.41,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "swePro_score": 21.41,
        "aggregate_score": 21.41
      }
    },
    {
      "modelId": "qwen-qwen3.5-0.8b",
      "modelName": "Qwen/Qwen3.5-0.8B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 0.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 20.8,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 11.9,
        "mmluPro_score": 29.7,
        "aggregate_score": 20.8
      }
    },
    {
      "modelId": "nvidia-nemotron-terminal-14b",
      "modelName": "nvidia/Nemotron-Terminal-14B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 14.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 20.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "terminalBench_score": 20.2,
        "aggregate_score": 20.2
      }
    },
    {
      "modelId": "openbmb-agentcpm-explore",
      "modelName": "openbmb/AgentCPM-Explore",
      "provider": "openbmb",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 19.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 19.1,
        "aggregate_score": 19.1
      }
    },
    {
      "modelId": "zai-org-glm-4.6",
      "modelName": "zai-org/GLM-4.6",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 356.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 17.09,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "swePro_score": 9.67,
        "terminalBench_score": 24.5,
        "aggregate_score": 17.09
      }
    }
  ],
  "models": [
    {
      "modelId": "meta-llama-llama-3.1-405b",
      "modelName": "meta-llama/Llama-3.1-405B",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 405.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 96.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 96.8,
        "aggregate_score": 96.8
      }
    },
    {
      "modelId": "microsoft-phi-3-medium-4k-instruct",
      "modelName": "microsoft/Phi-3-medium-4k-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 14,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 91,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 91,
        "aggregate_score": 91
      }
    },
    {
      "modelId": "qwen-qwen2-72b",
      "modelName": "Qwen/Qwen2-72B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 72.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 89.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 89.5,
        "aggregate_score": 89.5
      }
    },
    {
      "modelId": "microsoft-phi-3.5-mini-instruct",
      "modelName": "microsoft/Phi-3.5-mini-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 3.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 86.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 86.2,
        "aggregate_score": 86.2
      }
    },
    {
      "modelId": "internlm-internlm2_5-7b-chat",
      "modelName": "internlm/internlm2_5-7b-chat",
      "provider": "internlm",
      "modelType": "open",
      "parametersBillions": 7.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 86,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 86,
        "aggregate_score": 86
      }
    },
    {
      "modelId": "datalab-to-chandra-ocr-2",
      "modelName": "datalab-to/chandra-ocr-2",
      "provider": "datalab-to",
      "modelType": "open",
      "parametersBillions": 5.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 85.9,
        "aggregate_score": 85.9
      }
    },
    {
      "modelId": "microsoft-phi-3-mini-4k-instruct",
      "modelName": "microsoft/Phi-3-mini-4k-instruct",
      "provider": "microsoft",
      "modelType": "open",
      "parametersBillions": 3.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85.7,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 85.7,
        "aggregate_score": 85.7
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-r1-0528",
      "modelName": "deepseek-ai/DeepSeek-R1-0528",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 85,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 85,
        "aggregate_score": 85
      }
    },
    {
      "modelId": "qwen-qwen3-235b-a22b-thinking-2507",
      "modelName": "Qwen/Qwen3-235B-A22B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 84.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 84.4,
        "aggregate_score": 84.4
      }
    },
    {
      "modelId": "rednote-hilab-dots.mocr",
      "modelName": "rednote-hilab/dots.mocr",
      "provider": "rednote-hilab",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-4bit",
      "modelName": "mlx-community/dots.mocr-4bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-5bit",
      "modelName": "mlx-community/dots.mocr-5bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-6bit",
      "modelName": "mlx-community/dots.mocr-6bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-8bit",
      "modelName": "mlx-community/dots.mocr-8bit",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-bf16",
      "modelName": "mlx-community/dots.mocr-bf16",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-mxfp4",
      "modelName": "mlx-community/dots.mocr-mxfp4",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-mxfp8",
      "modelName": "mlx-community/dots.mocr-mxfp8",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "mlx-community-dots.mocr-nvfp4",
      "modelName": "mlx-community/dots.mocr-nvfp4",
      "provider": "mlx-community",
      "modelType": "open",
      "parametersBillions": 1.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.9,
        "aggregate_score": 83.9
      }
    },
    {
      "modelId": "lightonai-lightonocr-2-1b",
      "modelName": "lightonai/LightOnOCR-2-1B",
      "provider": "lightonai",
      "modelType": "open",
      "parametersBillions": 1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.2,
        "aggregate_score": 83.2
      }
    },
    {
      "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
      "modelName": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 30.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.15,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "aime2026_score": 87.5,
        "hmmt2026_score": 78.79,
        "aggregate_score": 83.15
      }
    },
    {
      "modelId": "datalab-to-chandra",
      "modelName": "datalab-to/chandra",
      "provider": "datalab-to",
      "modelType": "open",
      "parametersBillions": 8.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 83.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 83.1,
        "aggregate_score": 83.1
      }
    },
    {
      "modelId": "infly-infinity-parser-7b",
      "modelName": "infly/Infinity-Parser-7B",
      "provider": "infly",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.5,
        "aggregate_score": 82.5
      }
    },
    {
      "modelId": "allenai-olmocr-2-7b-1025-fp8",
      "modelName": "allenai/olmOCR-2-7B-1025-FP8",
      "provider": "allenai",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.4,
        "aggregate_score": 82.4
      }
    },
    {
      "modelId": "titanml-olmocr-2-7b-1025-fp8",
      "modelName": "TitanML/olmOCR-2-7B-1025-FP8",
      "provider": "TitanML",
      "modelType": "open",
      "parametersBillions": 8.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 82.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 82.4,
        "aggregate_score": 82.4
      }
    },
    {
      "modelId": "qwen-qwen3.5-9b",
      "modelName": "Qwen/Qwen3.5-9B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 9.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 81.98,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "aime2026_score": 92.5,
        "gpqa_score": 81.7,
        "hmmt2026_score": 71.21,
        "mmluPro_score": 82.5,
        "aggregate_score": 81.98
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3-0324",
      "modelName": "deepseek-ai/DeepSeek-V3-0324",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 81.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 81.2,
        "aggregate_score": 81.2
      }
    },
    {
      "modelId": "qwen-qwen3-next-80b-a3b-instruct",
      "modelName": "Qwen/Qwen3-Next-80B-A3B-Instruct",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 81.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 80.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 80.6,
        "aggregate_score": 80.6
      }
    },
    {
      "modelId": "paddlepaddle-paddleocr-vl",
      "modelName": "PaddlePaddle/PaddleOCR-VL",
      "provider": "PaddlePaddle",
      "modelType": "open",
      "parametersBillions": 1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 80,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 80,
        "aggregate_score": 80
      }
    },
    {
      "modelId": "qwen-qwen2-7b",
      "modelName": "Qwen/Qwen2-7B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 7.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.9,
        "aggregate_score": 79.9
      }
    },
    {
      "modelId": "baidu-qianfan-ocr",
      "modelName": "baidu/Qianfan-OCR",
      "provider": "baidu",
      "modelType": "open",
      "parametersBillions": 4.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 79.8,
        "aggregate_score": 79.8
      }
    },
    {
      "modelId": "internlm-internlm2-chat-20b",
      "modelName": "internlm/internlm2-chat-20b",
      "provider": "internlm",
      "modelType": "open",
      "parametersBillions": 19.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.6,
        "aggregate_score": 79.6
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v2",
      "modelName": "deepseek-ai/DeepSeek-V2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 235.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 79.2,
        "aggregate_score": 79.2
      }
    },
    {
      "modelId": "rednote-hilab-dots.ocr",
      "modelName": "rednote-hilab/dots.ocr",
      "provider": "rednote-hilab",
      "modelType": "open",
      "parametersBillions": 3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 79.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 79.1,
        "aggregate_score": 79.1
      }
    },
    {
      "modelId": "meituan-longcat-longcat-flash-lite",
      "modelName": "meituan-longcat/LongCat-Flash-Lite",
      "provider": "meituan-longcat",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 78.29,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 78.29,
        "aggregate_score": 78.29
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-r1",
      "modelName": "deepseek-ai/DeepSeek-R1",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.75,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 71.5,
        "mmluPro_score": 84,
        "aggregate_score": 77.75
      }
    },
    {
      "modelId": "jdopensource-joyai-llm-flash",
      "modelName": "jdopensource/JoyAI-LLM-Flash",
      "provider": "jdopensource",
      "modelType": "open",
      "parametersBillions": 49.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.72,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 74.43,
        "mmluPro_score": 81.02,
        "aggregate_score": 77.72
      }
    },
    {
      "modelId": "qwen-qwen3.5-4b",
      "modelName": "Qwen/Qwen3.5-4B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 77.65,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 76.2,
        "mmluPro_score": 79.1,
        "aggregate_score": 77.65
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3",
      "modelName": "deepseek-ai/DeepSeek-V3",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 684.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.85,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gsm8k_score": 89.3,
        "mmluPro_score": 64.4,
        "aggregate_score": 76.85
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-ocr-2",
      "modelName": "deepseek-ai/DeepSeek-OCR-2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 3.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.3,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 76.3,
        "aggregate_score": 76.3
      }
    },
    {
      "modelId": "lightonai-lightonocr-1b-1025",
      "modelName": "lightonai/LightOnOCR-1B-1025",
      "provider": "lightonai",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 76.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 76.1,
        "aggregate_score": 76.1
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-ocr",
      "modelName": "deepseek-ai/DeepSeek-OCR",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 3.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.7,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.7,
        "aggregate_score": 75.7
      }
    },
    {
      "modelId": "arcee-ai-trinity-large-preview",
      "modelName": "arcee-ai/Trinity-Large-Preview",
      "provider": "arcee-ai",
      "modelType": "open",
      "parametersBillions": 398.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "ares-realm-studios-trinity-large-preview-arstest",
      "modelName": "Ares-Realm-Studios/Trinity-Large-Preview-ARSTEST",
      "provider": "Ares-Realm-Studios",
      "modelType": "open",
      "parametersBillions": 398.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "opendatalab-mineru2.5-2509-1.2b",
      "modelName": "opendatalab/MinerU2.5-2509-1.2B",
      "provider": "opendatalab",
      "modelType": "open",
      "parametersBillions": 1.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "zai-org-glm-ocr",
      "modelName": "zai-org/GLM-OCR",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 75.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 75.2,
        "aggregate_score": 75.2
      }
    },
    {
      "modelId": "multilingual-multimodal-nlp-industrialcoder",
      "modelName": "Multilingual-Multimodal-NLP/IndustrialCoder",
      "provider": "Multilingual-Multimodal-NLP",
      "modelType": "open",
      "parametersBillions": 32,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 74.8,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 74.8,
        "aggregate_score": 74.8
      }
    },
    {
      "modelId": "qwen-qwen3.5-397b-a17b",
      "modelName": "Qwen/Qwen3.5-397B-A17B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 403.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 73.57,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 93.33,
        "gpqa_score": 88.4,
        "hle_score": 28.7,
        "hmmt2026_score": 87.88,
        "mmluPro_score": 87.8,
        "sweVerified_score": 76.4,
        "terminalBench_score": 52.5,
        "aggregate_score": 73.57
      }
    },
    {
      "modelId": "lm-provers-qed-nano",
      "modelName": "lm-provers/QED-Nano",
      "provider": "lm-provers",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 72.69,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "aime2026_score": 82.5,
        "hmmt2026_score": 62.88,
        "aggregate_score": 72.69
      }
    },
    {
      "modelId": "moonshotai-kimi-k2.5",
      "modelName": "moonshotai/Kimi-K2.5",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1058.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.57,
      "coverageCount": 8,
      "coveragePercent": 72.7,
      "scores": {
        "aime2026_score": 95.83,
        "gpqa_score": 87.6,
        "hle_score": 50.2,
        "hmmt2026_score": 87.12,
        "mmluPro_score": 87.1,
        "swePro_score": 50.7,
        "sweVerified_score": 70.8,
        "terminalBench_score": 43.2,
        "aggregate_score": 71.57
      }
    },
    {
      "modelId": "stepfun-ai-step-3.5-flash",
      "modelName": "stepfun-ai/Step-3.5-Flash",
      "provider": "stepfun-ai",
      "modelType": "open",
      "parametersBillions": 199.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.35,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 96.67,
        "gpqa_score": 83.5,
        "hle_score": 23.1,
        "hmmt2026_score": 86.36,
        "mmluPro_score": 84.4,
        "sweVerified_score": 74.4,
        "terminalBench_score": 51,
        "aggregate_score": 71.35
      }
    },
    {
      "modelId": "mistralai-mistral-small-4-119b-2603",
      "modelName": "mistralai/Mistral-Small-4-119B-2603",
      "provider": "mistralai",
      "modelType": "open",
      "parametersBillions": 119.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 71.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gpqa_score": 71.2,
        "aggregate_score": 71.2
      }
    },
    {
      "modelId": "zai-org-glm-5",
      "modelName": "zai-org/GLM-5",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 753.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 70.65,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "aime2026_score": 95.83,
        "gpqa_score": 86,
        "hle_score": 30.5,
        "hmmt2026_score": 86.36,
        "sweVerified_score": 72.8,
        "terminalBench_score": 52.4,
        "aggregate_score": 70.65
      }
    },
    {
      "modelId": "fireredteam-firered-ocr",
      "modelName": "FireRedTeam/FireRed-OCR",
      "provider": "FireRedTeam",
      "modelType": "open",
      "parametersBillions": 2.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 70.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 70.2,
        "aggregate_score": 70.2
      }
    },
    {
      "modelId": "nanonets-nanonets-ocr2-3b",
      "modelName": "nanonets/Nanonets-OCR2-3B",
      "provider": "nanonets",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 69.5,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "olmOcr_score": 69.5,
        "aggregate_score": 69.5
      }
    },
    {
      "modelId": "qwen-qwen3.5-27b",
      "modelName": "Qwen/Qwen3.5-27B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 27.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.83,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 90.83,
        "gpqa_score": 85.5,
        "hle_score": 24.3,
        "hmmt2026_score": 81.06,
        "mmluPro_score": 86.1,
        "sweVerified_score": 72.4,
        "terminalBench_score": 41.6,
        "aggregate_score": 68.83
      }
    },
    {
      "modelId": "qwen-qwen3-4b-thinking-2507",
      "modelName": "Qwen/Qwen3-4B-Thinking-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.83,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "aime2026_score": 82.5,
        "gpqa_score": 65.8,
        "hmmt2026_score": 53.03,
        "mmluPro_score": 74,
        "aggregate_score": 68.83
      }
    },
    {
      "modelId": "qwen-qwen3.5-35b-a3b",
      "modelName": "Qwen/Qwen3.5-35B-A3B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 36,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 68.11,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 93.33,
        "gpqa_score": 84.2,
        "hle_score": 22.4,
        "hmmt2026_score": 81.82,
        "mmluPro_score": 85.3,
        "sweVerified_score": 69.2,
        "terminalBench_score": 40.5,
        "aggregate_score": 68.11
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-instruct-0905",
      "modelName": "moonshotai/Kimi-K2-Instruct-0905",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1026.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 66.68,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "evasionBench_score": 66.68,
        "aggregate_score": 66.68
      }
    },
    {
      "modelId": "gair-openswe-72b",
      "modelName": "GAIR/OpenSWE-72B",
      "provider": "GAIR",
      "modelType": "open",
      "parametersBillions": 72.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 66,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 66,
        "aggregate_score": 66
      }
    },
    {
      "modelId": "qwen-qwen3-4b-instruct-2507",
      "modelName": "Qwen/Qwen3-4B-Instruct-2507",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 65.8,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 62,
        "mmluPro_score": 69.6,
        "aggregate_score": 65.8
      }
    },
    {
      "modelId": "deepseek-ai-deepseek-v3.2",
      "modelName": "deepseek-ai/DeepSeek-V3.2",
      "provider": "deepseek-ai",
      "modelType": "open",
      "parametersBillions": 685.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64.28,
      "coverageCount": 9,
      "coveragePercent": 81.8,
      "scores": {
        "aime2026_score": 94.17,
        "evasionBench_score": 66.88,
        "gpqa_score": 82.4,
        "hle_score": 40.8,
        "hmmt2026_score": 84.09,
        "mmluPro_score": 85,
        "swePro_score": 15.56,
        "sweVerified_score": 70,
        "terminalBench_score": 39.6,
        "aggregate_score": 64.28
      }
    },
    {
      "modelId": "zai-org-glm-4.7",
      "modelName": "zai-org/GLM-4.7",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 358.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64.15,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "evasionBench_score": 82.91,
        "gpqa_score": 85.7,
        "hle_score": 24.8,
        "mmluPro_score": 84.3,
        "sweVerified_score": 73.8,
        "terminalBench_score": 33.4,
        "aggregate_score": 64.15
      }
    },
    {
      "modelId": "qwen-qwen3.5-122b-a10b",
      "modelName": "Qwen/Qwen3.5-122B-A10B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 125.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 64,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 86.6,
        "hle_score": 25.3,
        "mmluPro_score": 86.7,
        "sweVerified_score": 72,
        "terminalBench_score": 49.4,
        "aggregate_score": 64
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 123.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 62.97,
      "coverageCount": 7,
      "coveragePercent": 63.6,
      "scores": {
        "aime2026_score": 90,
        "gpqa_score": 79.23,
        "hle_score": 18.26,
        "hmmt2026_score": 84.85,
        "mmluPro_score": 83.73,
        "sweVerified_score": 53.73,
        "terminalBench_score": 31,
        "aggregate_score": 62.97
      }
    },
    {
      "modelId": "gair-openswe-32b",
      "modelName": "GAIR/OpenSWE-32B",
      "provider": "GAIR",
      "modelType": "open",
      "parametersBillions": 32.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 62.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 62.4,
        "aggregate_score": 62.4
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-thinking",
      "modelName": "moonshotai/Kimi-K2-Thinking",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1058.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 60,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 84.5,
        "hle_score": 23.9,
        "mmluPro_score": 84.6,
        "sweVerified_score": 71.3,
        "terminalBench_score": 35.7,
        "aggregate_score": 60
      }
    },
    {
      "modelId": "minimaxai-minimax-m2.5",
      "modelName": "MiniMaxAI/MiniMax-M2.5",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 58.95,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "gpqa_score": 85.2,
        "hle_score": 19.4,
        "swePro_score": 55.4,
        "sweVerified_score": 75.8,
        "aggregate_score": 58.95
      }
    },
    {
      "modelId": "lgai-exaone-k-exaone-236b-a23b",
      "modelName": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "provider": "LGAI-EXAONE",
      "modelType": "open",
      "parametersBillions": 237.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 58.83,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 79.1,
        "hle_score": 13.6,
        "mmluPro_score": 83.8,
        "aggregate_score": 58.83
      }
    },
    {
      "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
      "modelName": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 57.87,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 76.1,
        "hle_score": 17.7,
        "mmluPro_score": 79.8,
        "aggregate_score": 57.87
      }
    },
    {
      "modelId": "qwen-qwen3.5-2b",
      "modelName": "Qwen/Qwen3.5-2B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 2.3,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 55.3,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "mmluPro_score": 55.3,
        "aggregate_score": 55.3
      }
    },
    {
      "modelId": "meta-llama-llama-3.1-8b-instruct",
      "modelName": "meta-llama/Llama-3.1-8B-Instruct",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 54.4,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 30.4,
        "gsm8k_score": 84.5,
        "mmluPro_score": 48.3,
        "aggregate_score": 54.4
      }
    },
    {
      "modelId": "facebook-cwm",
      "modelName": "facebook/cwm",
      "provider": "facebook",
      "modelType": "open",
      "parametersBillions": 32.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.9,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 53.9,
        "aggregate_score": 53.9
      }
    },
    {
      "modelId": "minimaxai-minimax-m2.1",
      "modelName": "MiniMaxAI/MiniMax-M2.1",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.59,
      "coverageCount": 6,
      "coveragePercent": 54.5,
      "scores": {
        "evasionBench_score": 71.31,
        "hle_score": 22.2,
        "mmluPro_score": 88,
        "swePro_score": 36.81,
        "sweVerified_score": 74,
        "terminalBench_score": 29.2,
        "aggregate_score": 53.59
      }
    },
    {
      "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
      "modelName": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "provider": "RedHatAI",
      "modelType": "open",
      "parametersBillions": 123.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 53.19,
      "coverageCount": 5,
      "coveragePercent": 45.5,
      "scores": {
        "gpqa_score": 79.23,
        "hle_score": 18.26,
        "mmluPro_score": 83.73,
        "sweVerified_score": 53.73,
        "terminalBench_score": 31,
        "aggregate_score": 53.19
      }
    },
    {
      "modelId": "meituan-longcat-longcat-flash-thinking-2601",
      "modelName": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "provider": "meituan-longcat",
      "modelType": "open",
      "parametersBillions": 561.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 52.85,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 80.5,
        "hle_score": 25.2,
        "aggregate_score": 52.85
      }
    },
    {
      "modelId": "swe-lego-swe-lego-qwen3-32b",
      "modelName": "SWE-Lego/SWE-Lego-Qwen3-32B",
      "provider": "SWE-Lego",
      "modelType": "open",
      "parametersBillions": 0,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 52.6,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 52.6,
        "aggregate_score": 52.6
      }
    },
    {
      "modelId": "snurfyai-sn-logicer-0.8b",
      "modelName": "SnurfyAI/Sn-Logicer-0.8B",
      "provider": "SnurfyAI",
      "modelType": "open",
      "parametersBillions": 0.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 50.57,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gsm8k_score": 50.57,
        "aggregate_score": 50.57
      }
    },
    {
      "modelId": "qwen-qwen3-coder-next",
      "modelName": "Qwen/Qwen3-Coder-Next",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 79.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 50.37,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "swePro_score": 44.3,
        "sweVerified_score": 70.6,
        "terminalBench_score": 36.2,
        "aggregate_score": 50.37
      }
    },
    {
      "modelId": "zai-org-glm-4.7-flash",
      "modelName": "zai-org/GLM-4.7-Flash",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 31.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 49.6,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 75.2,
        "hle_score": 14.4,
        "sweVerified_score": 59.2,
        "aggregate_score": 49.6
      }
    },
    {
      "modelId": "minimaxai-minimax-m2",
      "modelName": "MiniMaxAI/MiniMax-M2",
      "provider": "MiniMaxAI",
      "modelType": "open",
      "parametersBillions": 228.7,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 48.48,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "hle_score": 12.5,
        "mmluPro_score": 82,
        "sweVerified_score": 69.4,
        "terminalBench_score": 30,
        "aggregate_score": 48.48
      }
    },
    {
      "modelId": "nanbeige-nanbeige4.1-3b",
      "modelName": "Nanbeige/Nanbeige4.1-3B",
      "provider": "Nanbeige",
      "modelType": "open",
      "parametersBillions": 3.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 48.2,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 83.8,
        "hle_score": 12.6,
        "aggregate_score": 48.2
      }
    },
    {
      "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
      "modelName": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 480.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 46.92,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "evasionBench_score": 78.16,
        "swePro_score": 38.7,
        "terminalBench_score": 23.9,
        "aggregate_score": 46.92
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 46.9,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 15.5,
        "mmluPro_score": 78.3,
        "aggregate_score": 46.9
      }
    },
    {
      "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
      "modelName": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 31.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 44.15,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 10.2,
        "mmluPro_score": 78.1,
        "aggregate_score": 44.15
      }
    },
    {
      "modelId": "swe-lego-swe-lego-qwen3-8b",
      "modelName": "SWE-Lego/SWE-Lego-Qwen3-8B",
      "provider": "SWE-Lego",
      "modelType": "open",
      "parametersBillions": 0,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 42.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "sweVerified_score": 42.2,
        "aggregate_score": 42.2
      }
    },
    {
      "modelId": "tiiuae-falcon-h1r-7b",
      "modelName": "tiiuae/Falcon-H1R-7B",
      "provider": "tiiuae",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 41.6,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "hle_score": 11.1,
        "mmluPro_score": 72.1,
        "aggregate_score": 41.6
      }
    },
    {
      "modelId": "miromind-ai-mirothinker-v1.5-235b",
      "modelName": "miromind-ai/MiroThinker-v1.5-235B",
      "provider": "miromind-ai",
      "modelType": "open",
      "parametersBillions": 235.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 39.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 39.2,
        "aggregate_score": 39.2
      }
    },
    {
      "modelId": "liquidai-lfm2.5-1.2b-instruct",
      "modelName": "LiquidAI/LFM2.5-1.2B-Instruct",
      "provider": "LiquidAI",
      "modelType": "open",
      "parametersBillions": 1.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 38.89,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "gpqa_score": 38.89,
        "aggregate_score": 38.89
      }
    },
    {
      "modelId": "nvidia-nemotron-orchestrator-8b",
      "modelName": "nvidia/Nemotron-Orchestrator-8B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": null,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 37.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 37.1,
        "aggregate_score": 37.1
      }
    },
    {
      "modelId": "openai-gpt-oss-120b",
      "modelName": "openai/gpt-oss-120b",
      "provider": "openai",
      "modelType": "open",
      "parametersBillions": 120.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 34.1,
      "coverageCount": 4,
      "coveragePercent": 36.4,
      "scores": {
        "gpqa_score": 67.1,
        "hle_score": 5.2,
        "swePro_score": 16.2,
        "sweVerified_score": 47.9,
        "aggregate_score": 34.1
      }
    },
    {
      "modelId": "openai-gpt-oss-20b",
      "modelName": "openai/gpt-oss-20b",
      "provider": "openai",
      "modelType": "open",
      "parametersBillions": 21.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 32.8,
      "coverageCount": 3,
      "coveragePercent": 27.3,
      "scores": {
        "gpqa_score": 56.8,
        "hle_score": 4.2,
        "sweVerified_score": 37.4,
        "aggregate_score": 32.8
      }
    },
    {
      "modelId": "miromind-ai-mirothinker-v1.5-30b",
      "modelName": "miromind-ai/MiroThinker-v1.5-30B",
      "provider": "miromind-ai",
      "modelType": "open",
      "parametersBillions": 30.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 31,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 31,
        "aggregate_score": 31
      }
    },
    {
      "modelId": "moonshotai-kimi-k2-instruct",
      "modelName": "moonshotai/Kimi-K2-Instruct",
      "provider": "moonshotai",
      "modelType": "open",
      "parametersBillions": 1026.5,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 27.73,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "swePro_score": 27.67,
        "terminalBench_score": 27.8,
        "aggregate_score": 27.73
      }
    },
    {
      "modelId": "nvidia-nemotron-terminal-32b",
      "modelName": "nvidia/Nemotron-Terminal-32B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 32.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 27.4,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "terminalBench_score": 27.4,
        "aggregate_score": 27.4
      }
    },
    {
      "modelId": "xiaomimimo-mimo-v2-flash",
      "modelName": "XiaomiMiMo/MiMo-V2-Flash",
      "provider": "XiaomiMiMo",
      "modelType": "open",
      "parametersBillions": 309.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 22.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 22.1,
        "aggregate_score": 22.1
      }
    },
    {
      "modelId": "qwen-qwen3-235b-a22b",
      "modelName": "Qwen/Qwen3-235B-A22B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 235.1,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 21.41,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "swePro_score": 21.41,
        "aggregate_score": 21.41
      }
    },
    {
      "modelId": "qwen-qwen3.5-0.8b",
      "modelName": "Qwen/Qwen3.5-0.8B",
      "provider": "Qwen",
      "modelType": "open",
      "parametersBillions": 0.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 20.8,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "gpqa_score": 11.9,
        "mmluPro_score": 29.7,
        "aggregate_score": 20.8
      }
    },
    {
      "modelId": "nvidia-nemotron-terminal-14b",
      "modelName": "nvidia/Nemotron-Terminal-14B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 14.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 20.2,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "terminalBench_score": 20.2,
        "aggregate_score": 20.2
      }
    },
    {
      "modelId": "openbmb-agentcpm-explore",
      "modelName": "openbmb/AgentCPM-Explore",
      "provider": "openbmb",
      "modelType": "open",
      "parametersBillions": 4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 19.1,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 19.1,
        "aggregate_score": 19.1
      }
    },
    {
      "modelId": "zai-org-glm-4.6",
      "modelName": "zai-org/GLM-4.6",
      "provider": "zai-org",
      "modelType": "open",
      "parametersBillions": 356.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 17.09,
      "coverageCount": 2,
      "coveragePercent": 18.2,
      "scores": {
        "swePro_score": 9.67,
        "terminalBench_score": 24.5,
        "aggregate_score": 17.09
      }
    },
    {
      "modelId": "nvidia-nemotron-terminal-8b",
      "modelName": "nvidia/Nemotron-Terminal-8B",
      "provider": "nvidia",
      "modelType": "open",
      "parametersBillions": 8.2,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 13,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "terminalBench_score": 13,
        "aggregate_score": 13
      }
    },
    {
      "modelId": "google-gemma-3-27b-it",
      "modelName": "google/gemma-3-27b-it",
      "provider": "google",
      "modelType": "open",
      "parametersBillions": 27.4,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 11.38,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "swePro_score": 11.38,
        "aggregate_score": 11.38
      }
    },
    {
      "modelId": "meta-llama-llama-3.1-405b-instruct",
      "modelName": "meta-llama/Llama-3.1-405B-Instruct",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 405.9,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 11.18,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "swePro_score": 11.18,
        "aggregate_score": 11.18
      }
    },
    {
      "modelId": "helpingai-dhanishtha-2.0-0126",
      "modelName": "HelpingAI/Dhanishtha-2.0-0126",
      "provider": "HelpingAI",
      "modelType": "open",
      "parametersBillions": 14.8,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 9.92,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "hle_score": 9.92,
        "aggregate_score": 9.92
      }
    },
    {
      "modelId": "meta-llama-llama-4-maverick-17b-128e-instruct",
      "modelName": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
      "provider": "meta-llama",
      "modelType": "open",
      "parametersBillions": 401.6,
      "license": "Unknown",
      "contextWindow": 0,
      "modality": "text",
      "architecture": "Transformer",
      "aggregateScore": 5.24,
      "coverageCount": 1,
      "coveragePercent": 9.1,
      "scores": {
        "swePro_score": 5.24,
        "aggregate_score": 5.24
      }
    }
  ]
}
