{
  "api_version": "1",
  "updated": "2026-10-24",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "story": {
    "slug": "china-leads-on-automationbench",
    "title": "China Leads on AutomationBench",
    "description": "AutomationBench scores from Chinese labs and from OpenAI, Anthropic and Google, by release date, as each lab reports them.",
    "url": "https://frontierlog.ai/stories/china-leads-on-automationbench",
    "date": "2026-10-24",
    "image": "https://frontierlog.ai/og/story-china-leads-on-automationbench-lead.png",
    "event": "2026-10-17-deepseek-v4-1-flash-1017",
    "tags": [
      "agents",
      "open-weights"
    ],
    "images": [
      "https://frontierlog.ai/og/story-china-leads-on-automationbench-lead.png"
    ],
    "steps": [],
    "tables": [
      {
        "title": "AutomationBench, Chinese labs",
        "unit": "%",
        "rows": [
          {
            "event": "2026-04-24-deepseek-v4-preview",
            "date": "2026-04-24",
            "provider": "deepseek",
            "value": 12.8,
            "printed": "12.8",
            "source": "https://api-docs.deepseek.com/news/news260813/",
            "where": "later report: DeepSeek-V4-Pro GA post, table image, row 'AutomationBench (Public)', column 'DeepSeek-V4-Pro-Preview'"
          },
          {
            "event": "2026-05-20-qwen3-7-max",
            "date": "2026-05-20",
            "provider": "alibaba",
            "value": 14.2,
            "printed": "14.2",
            "source": "https://qwen.ai/blog?id=qwen3.8",
            "where": "Qwen3.8 post, 'Full Benchmark Table', row 'Automation-Bench (Pass@1)', column 'Qwen3.7-Max'"
          },
          {
            "event": "2026-06-16-glm-5-2",
            "date": "2026-06-16",
            "provider": "zai",
            "value": 26.2,
            "printed": "26.2",
            "source": "https://z.ai/blog/glm-5.3",
            "where": "'Performance across comparison models' table, row 'AutomationBench v1.0.6', column 'GLM-5.2'"
          },
          {
            "event": "2026-07-16-kimi-k3",
            "date": "2026-07-16",
            "provider": "moonshot",
            "value": 30.8,
            "printed": "30.8",
            "source": "https://www.kimi.ai/blog/kimi-k3",
            "where": "'Full Benchmark Table', row 'Automation Bench' (Agentic), column 'Kimi K3 (max)'"
          },
          {
            "event": "2026-08-03-qwen3-8-max",
            "date": "2026-08-03",
            "provider": "alibaba",
            "value": 27.3,
            "printed": "27.3",
            "source": "https://qwen.ai/blog?id=qwen3.8",
            "where": "'Full Benchmark Table' (first, language/agent HTML table), General Agent section, row 'Automation-Bench (Pass@1)', column 'Qwen3.8-Max'"
          },
          {
            "event": "2026-08-13-deepseek-v4-pro-ga",
            "date": "2026-08-13",
            "provider": "deepseek",
            "value": 31.8,
            "printed": "31.8",
            "source": "https://api-docs.deepseek.com/news/news260813/",
            "where": "table image, row 'AutomationBench (Public)', column 'DeepSeek-V4-Pro-0813'"
          },
          {
            "event": "2026-08-14-glm-5-3",
            "date": "2026-08-14",
            "provider": "zai",
            "value": 48.2,
            "printed": "48.2",
            "source": "https://z.ai/blog/glm-5.3",
            "where": "'Performance across comparison models' table, row 'AutomationBench v1.0.6', column 'GLM-5.3'"
          },
          {
            "event": "2026-08-21-deepseek-v4-flash-vision-exp",
            "date": "2026-08-21",
            "provider": "deepseek",
            "value": 25.7,
            "printed": "25.7",
            "source": "https://api-docs.deepseek.com/news/news260821/",
            "where": "table image, section 'Text-Based Agent Evaluation', row 'AutomationBench (Public)', column 'DeepSeek V4-Flash-Vision-Exp'"
          },
          {
            "event": "2026-08-26-glm-5-3-flash",
            "date": "2026-08-26",
            "provider": "zai",
            "value": 48.8,
            "printed": "48.8",
            "source": "https://z.ai/blog/glm-5.3-flash",
            "where": "main benchmark table (second table), AGENTIC block, row 'AutomationBench v1.0.6', column 'GLM-5.3-Flash'"
          },
          {
            "event": "2026-09-10-deepseek-v4-1-flash",
            "date": "2026-09-10",
            "provider": "deepseek",
            "value": 54.8,
            "printed": "54.8",
            "source": "https://api-docs.deepseek.com/news/news260910/",
            "where": "benchmark table image (second image), row 'Automation-Bench', column 'DeepSeek V4.1-Flash' (the first chart image, v4.1_260910_benchmark.png, prints the same value label)"
          },
          {
            "event": "2026-10-17-deepseek-v4-1-flash-1017",
            "date": "2026-10-17",
            "provider": "deepseek",
            "value": 60.5,
            "printed": "60.5",
            "source": "https://api-docs.deepseek.com/news/news261017/",
            "where": "benchmark table image (first image), row 'Automation-Bench V1.0.6', column 'DeepSeek V4.1-Flash-1017'"
          }
        ]
      },
      {
        "title": "AutomationBench, OpenAI, Anthropic and Google",
        "unit": "%",
        "rows": [
          {
            "event": "2026-04-23-gpt-5-5",
            "date": "2026-04-23",
            "provider": "openai",
            "value": 12.9,
            "printed": "12.9%",
            "source": "https://openai.com/index/gpt-5-6",
            "where": "tool-use table (columns GPT-5.6 Sol, Terra, Luna, GPT-5.5, ...), row 'AutomationBench', column 'GPT-5.5'"
          },
          {
            "event": "2026-05-28-claude-opus-4-8",
            "date": "2026-05-28",
            "provider": "anthropic",
            "value": 15.5,
            "printed": "15.5",
            "source": "https://www.anthropic.com/claude-opus-4-8-system-card",
            "where": "Section 8.1, Table 8.1.A (evaluation summary), row 'Automation Bench', column 'Claude Opus 4.8'"
          },
          {
            "event": "2026-06-09-claude-fable-5-mythos-5",
            "date": "2026-06-09",
            "provider": "anthropic",
            "value": 17.4,
            "printed": "17.4",
            "source": "https://www.anthropic.com/claude-fable-5-mythos-5-system-card",
            "where": "Section 8.1, Table 8.1.A, row 'AutomationBench', column 'Fable 5'"
          },
          {
            "event": "2026-06-30-claude-sonnet-5",
            "date": "2026-06-30",
            "provider": "anthropic",
            "value": 13.5,
            "printed": "13.5",
            "source": "https://www.anthropic.com/claude-sonnet-5-system-card",
            "where": "Section 8.1, Table 8.1.A, row 'AutomationBench', column 'Claude Sonnet 5'"
          },
          {
            "event": "2026-07-09-gpt-5-6",
            "date": "2026-07-09",
            "provider": "openai",
            "value": 18.1,
            "printed": "18.1%",
            "source": "https://openai.com/index/gpt-5-6",
            "where": "tool-use table (columns GPT-5.6 Sol, Terra, Luna, GPT-5.5, ...), row 'AutomationBench', column 'GPT-5.6 Sol'"
          },
          {
            "event": "2026-07-21-gemini-3-6-flash-and-3-5-flash",
            "date": "2026-07-21",
            "provider": "google",
            "value": 17.0,
            "printed": "17.0%",
            "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/",
            "where": "benchmark table (image), row 'AutomationBench (Private set)', column 'Gemini 3.6 Flash'"
          },
          {
            "event": "2026-07-24-claude-opus-5",
            "date": "2026-07-24",
            "provider": "anthropic",
            "value": 26.0,
            "printed": "26.0%",
            "source": "https://www.anthropic.com/news/claude-opus-5",
            "where": "benchmark table (image), row 'Business workflows, AutomationBench', column 'Opus 5'"
          },
          {
            "event": "2026-08-13-gemini-3-7-flash",
            "date": "2026-08-13",
            "provider": "google",
            "value": 30.4,
            "printed": "30.4%",
            "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/",
            "where": "benchmark table (image), row 'AutomationBench (Private set)', column 'Gemini 3.7 Flash'"
          },
          {
            "event": "2026-09-01-claude-fable-5-1-mythos-5-1",
            "date": "2026-09-01",
            "provider": "anthropic",
            "value": 31.4,
            "printed": "31.4%",
            "source": "https://www.anthropic.com/claude-fable-and-mythos-5-1",
            "where": "benchmark table (HTML), row 'Business workflows, AutomationBench', column 'Fable 5.1'"
          },
          {
            "event": "2026-09-03-gpt-6-astra",
            "date": "2026-09-03",
            "provider": "openai",
            "value": 41.4,
            "printed": "41.4%",
            "source": "https://openai.com/index/gpt-6-astra",
            "where": "Professional table, row 'AutomationBench', column 'GPT‑6 Astra'"
          },
          {
            "event": "2026-09-22-claude-opus-5-5",
            "date": "2026-09-22",
            "provider": "anthropic",
            "value": 40.0,
            "printed": "40.0%",
            "source": "https://www.anthropic.com/claude-opus-5-5",
            "where": "benchmark table, row 'AutomationBench', column 'Opus 5.5'"
          },
          {
            "event": "2026-09-22-gpt-6-sol-and-luna",
            "date": "2026-09-22",
            "provider": "openai",
            "value": 33.2,
            "printed": "33.2%",
            "source": "https://openai.com/index/introducing-gpt-6-sol-and-luna",
            "where": "AutomationBench table (Model (and effort) / Score / Cost per task), row 'GPT-6 Sol (xhigh)', column 'Score'"
          },
          {
            "event": "2026-09-28-claude-sonnet-5-5",
            "date": "2026-09-28",
            "provider": "anthropic",
            "value": 44.7,
            "printed": "44.7",
            "source": "https://www.anthropic.com/claude-sonnet-5-5-system-card",
            "where": "Section 8.1, Table 8.1.A, row 'AutomationBench', column 'Claude Sonnet 5.5'"
          },
          {
            "event": "2026-09-30-gemini-4-argon",
            "date": "2026-09-30",
            "provider": "google",
            "value": 51.3,
            "printed": "51.3%",
            "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/",
            "where": "benchmark table (image), row 'AutomationBench', 'Score', column 'Gemini 4 Argon'"
          }
        ]
      },
      {
        "title": "AutomationBench, Meta",
        "unit": "%",
        "rows": [
          {
            "event": "2026-08-05-muse-spark-1-2",
            "date": "2026-08-05",
            "provider": "meta",
            "value": 38.2,
            "printed": "38.2",
            "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
            "where": "Muse Spark 1.3 scorecard (image), row 'AutomationBench', column 'Muse Spark 1.2 (xhigh)'"
          },
          {
            "event": "2026-09-02-muse-spark-1-3",
            "date": "2026-09-02",
            "provider": "meta",
            "value": 49.6,
            "printed": "49.6",
            "source": "https://research.meta.ai/blog/introducing-muse-spark-1-3",
            "where": "scorecard (image), row 'AutomationBench', column 'Muse Spark 1.3 (max)'"
          }
        ]
      }
    ],
    "sources": [
      "https://api-docs.deepseek.com/news/news260813/",
      "https://api-docs.deepseek.com/news/news260821/",
      "https://api-docs.deepseek.com/news/news260910/",
      "https://api-docs.deepseek.com/news/news261017/",
      "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/",
      "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/",
      "https://openai.com/index/gpt-5-6",
      "https://openai.com/index/gpt-6-astra",
      "https://openai.com/index/introducing-gpt-6-sol-and-luna",
      "https://qwen.ai/blog?id=qwen3.8",
      "https://research.meta.ai/blog/introducing-muse-spark-1-3",
      "https://www.anthropic.com/claude-fable-5-mythos-5-system-card",
      "https://www.anthropic.com/claude-fable-and-mythos-5-1",
      "https://www.anthropic.com/claude-opus-4-8-system-card",
      "https://www.anthropic.com/claude-opus-5-5",
      "https://www.anthropic.com/claude-sonnet-5-5-system-card",
      "https://www.anthropic.com/claude-sonnet-5-system-card",
      "https://www.anthropic.com/news/claude-opus-5",
      "https://www.kimi.ai/blog/kimi-k3",
      "https://z.ai/blog/glm-5.3",
      "https://z.ai/blog/glm-5.3-flash"
    ]
  }
}