{
  "source": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/raw/main/README.md",
  "model_names": [
    "DeepSeek V4.1 Flash 1017",
    "DeepSeek V4.1 Flash",
    "K3",
    "GLM-5.3",
    "GPT-5.6 Sol",
    "Opus 5"
  ],
  "highlight_index": 0,
  "series": [
    {
      "id": "01-deepswe",
      "title": "Software engineering",
      "benchmark": "DeepSWE v1.1",
      "values": [
        77.0,
        74.2,
        67.5,
        66.9,
        73.0,
        74.0
      ],
      "note": "Mini-SWE-V2 harness. Publisher-reported benchmark scores."
    },
    {
      "id": "02-terminal",
      "title": "Terminal tasks",
      "benchmark": "Terminal-Bench 4.0",
      "values": [
        42.3,
        31.2,
        12.6,
        37.9,
        39.9,
        51.8
      ],
      "note": "Claude Code harness. Publisher-reported benchmark scores."
    },
    {
      "id": "03-hle",
      "title": "Reasoning without tools",
      "benchmark": "HLE without tools",
      "values": [
        42.6,
        36.8,
        43.5,
        null,
        44.5,
        56.3
      ],
      "note": "Full HLE figures only. GLM-5.3 omitted: the source gives a text-only subset score."
    },
    {
      "id": "04-program",
      "title": "Programming tasks",
      "benchmark": "ProgramBench",
      "values": [
        29.1,
        20.3,
        17.5,
        19.0,
        23.0,
        37.0
      ],
      "note": "Publisher-reported benchmark scores. Additional per-row settings are not specified."
    },
    {
      "id": "05-nl2repo",
      "title": "From instructions to repositories",
      "benchmark": "NL2Repo-Bench",
      "values": [
        68.2,
        65.4,
        58.0,
        58.0,
        56.8,
        75.3
      ],
      "note": "Publisher-reported benchmark scores. Additional per-row settings are not specified."
    },
    {
      "id": "06-automation",
      "title": "Automation tasks",
      "benchmark": "Automation-Bench v1.0.6",
      "values": [
        60.5,
        54.8,
        46.7,
        48.8,
        45.8,
        50.3
      ],
      "note": "Publisher-reported benchmark scores. Additional per-row settings are not specified."
    },
    {
      "id": "07-agents",
      "title": "Agent evaluation",
      "benchmark": "Agents’ Last Exam",
      "values": [
        35.4,
        31.8,
        27.6,
        28.5,
        26.7,
        28.6
      ],
      "note": "Publisher-reported benchmark scores. Additional per-row settings are not specified."
    },
    {
      "id": "08-apex",
      "title": "Apex benchmark",
      "benchmark": "Apex Bench v1.1",
      "values": [
        72.1,
        64.6,
        47.8,
        56.6,
        54.3,
        65.8
      ],
      "note": "Publisher-reported benchmark scores. Additional per-row settings are not specified."
    }
  ],
  "branding_name": "Unbind Flash V1",
  "highlight_display_label": "Unbind Flash V1 · base model"
}