{
  "protocolVersion": "0.3.0",
  "name": "SociaBench",
  "description": "Read-only data from SociaBench (AI Social Intelligence Leaderboards): benchmarks, leaderboards, model results, reproduction reports and evaluation protocols. The leaderboards include only evaluations this platform ran under the current protocol version. Results published by the authors are listed separately in the original leaderboard, do not count toward the ranking, and cannot be compared with it directly. When you cite, credit \"SociaBench (AI Social Intelligence Leaderboards)\" with the link to the page, and give the formal name and original source of each benchmark. Text is American English by default; the tools that return page or benchmark text take a `language` argument (en-US or zh-CN). This agent does not use a language model: a request names a skill and its parameters in a data part, or gives a benchmark ID, benchmark name or page path as text.",
  "version": "1.0.0",
  "url": "https://sociabench.com/a2a",
  "preferredTransport": "JSONRPC",
  "supportedInterfaces": [
    {
      "url": "https://sociabench.com/a2a",
      "transport": "JSONRPC",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "0.3.0"
    }
  ],
  "additionalInterfaces": [
    {
      "url": "https://sociabench.com/a2a",
      "transport": "JSONRPC"
    }
  ],
  "provider": {
    "organization": "SociaBench",
    "url": "https://sociabench.com"
  },
  "documentationUrl": "https://sociabench.com/api.md#a2a",
  "iconUrl": "https://sociabench.com/apple-touch-icon.png",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false
  },
  "defaultInputModes": [
    "application/json",
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/markdown"
  ],
  "skills": [
    {
      "id": "list_benchmarks",
      "name": "List benchmarks",
      "description": "Lists every benchmark SociaBench covers: ID, name, category, summary, original source, and the addresses of its leaderboard and reproduction report.",
      "tags": [
        "SociaBench",
        "AI social intelligence",
        "leaderboards"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "text/markdown"
      ],
      "examples": [
        "{\"skill\": \"list_benchmarks\"}",
        "list benchmarks"
      ]
    },
    {
      "id": "get_leaderboard",
      "name": "Get leaderboard",
      "description": "Reads a benchmark's leaderboard (live data): the platform's ranking (overall score for every view, 95% confidence interval, group scores, sample count, evaluation time and data version), plus the original leaderboard of results published by the authors (listed separately, not part of the ranking).",
      "tags": [
        "SociaBench",
        "AI social intelligence",
        "leaderboards"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "text/markdown"
      ],
      "examples": [
        "{\"skill\": \"get_leaderboard\", \"benchmark\": \"characterbench\"}",
        "{\"skill\": \"get_leaderboard\", \"benchmark\": \"characterbench\", \"language\": \"zh-CN\"}",
        "characterbench"
      ]
    },
    {
      "id": "get_model_result",
      "name": "Get model result",
      "description": "Reads a model's platform evaluation result on a benchmark (live data): its rank in each view, overall score and confidence interval, group and by-dimension scores, model version and evaluation time. Only models this platform evaluated have a result page; models that appear only in the original leaderboard do not.",
      "tags": [
        "SociaBench",
        "AI social intelligence",
        "leaderboards"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "text/markdown"
      ],
      "examples": [
        "{\"skill\": \"get_model_result\", \"benchmark\": \"characterbench\", \"model\": \"deepseek-v4-1-flash-261017\"}"
      ]
    },
    {
      "id": "get_page",
      "name": "Get page",
      "description": "Reads the Markdown version of any public SociaBench page, for example the reproduction report /b/characterbench/methodology, the research list /methodology or the Data Platform Terms /data-terms.",
      "tags": [
        "SociaBench",
        "AI social intelligence",
        "reproduction report"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "text/markdown"
      ],
      "examples": [
        "{\"skill\": \"get_page\", \"path\": \"/b/characterbench/methodology\"}",
        "/b/coser/methodology",
        "/zh-CN/b/coser/methodology"
      ]
    },
    {
      "id": "get_protocol",
      "name": "Get evaluation protocol",
      "description": "Reads a benchmark's full evaluation protocol on this platform (JSON): protocol version, the prompts of the model under test and the judge, judge configuration, scoring rules and run parameters, for checking and reproduction.",
      "tags": [
        "SociaBench",
        "AI social intelligence",
        "evaluation protocol"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "text/markdown"
      ],
      "examples": [
        "{\"skill\": \"get_protocol\", \"benchmark\": \"minimax-rp\"}"
      ]
    }
  ]
}