Evidence row 1734419

What was observed

{
  "count": 7,
  "tools": [
    {
      "description": "What BenchLeader is, how the BenchLeader Index is computed, the current method version, data date and update cadence, coverage counts, licence and how to cite it.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {},
        "type": "object"
      },
      "name": "about_benchleader"
    },
    {
      "description": "Head-to-head comparison of two models with BenchLeader's verdict: who leads on quality (a lead is claimed only outside the combined margin of error), price and speed ratios, category-by-category wins, when to choose each, and shared benchmark results. Links the comparison page.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "effort_a": {
            "description": "Reasoning effort for model_a (defaults to its best-ranked configuration).",
            "type": "string"
          },
          "effort_b": {
            "description": "Reasoning effort for model_b (defaults to its best-ranked configuration).",
            "type": "string"
          },
          "model_a": {
            "description": "First model: id, configuration id, page URL or name.",
            "type": "string"
          },
          "model_b": {
            "description": "Second model: id, configuration id, page URL or name.",
            "type": "string"
          }
        },
        "required": [
          "model_a",
          "model_b"
        ],
        "type": "object"
      },
      "name": "compare_models"
    },
    {
      "description": "One benchmark: what it measures, unit, publisher and source, whether and how much it counts in the BenchLeader Index, status and caveats, and its top models (one row per model, best result first).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "benchmark": {
            "description": "Benchmark id (\"gpqa_diamond\"), name (\"SWE-bench Verified\"), alias or page URL.",
            "type": "string"
          },
          "limit": {
            "default": 10,
            "description": "How many top models to return (at most 25).",
            "maximum": 25,
            "minimum": 1,
            "type": "integer"
          }
        },
        "required": [
          "benchmark"
        ],
        "type": "object"
      },
      "name": "get_benchmark"
    },
    {
      "description": "The BenchLeader Index leaderboard of large language models: a daily composite of independent public benchmarks, one row per model (its best reasoning-effort configuration) as on the homepage. Optionally rank by one category score (coding, agentic, reasoning, math, knowledge…), list every model × effort configuration, or filter to open-weights models or one developer. Paged.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "category": {
            "description": "Rank by this category score instead of the overall Index, e.g. coding, agentic, reasoning, math, knowledge, instruction, multimodal, long_context.",
            "type": "string"
          },
          "configurations": {
            "default": false,
            "description": "List every ranked model × reasoning-effort configuration rather than one row per model.",
            "type": "boolean"
          },
          "developer": {
            "description": "Only models from this developer, e.g. OpenAI, Anthropic, Google, DeepSeek.",
            "type": "string"
          },
          "limit": {
            "default": 20,
            "description": "How many rows to return (at most 100).",
            "maximum": 100,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "Rows to skip, for paging (use next_offset from the previous page).",
            "minimum": 0,
            "type": "integer"
          },
          "open_weights_only": {
            "default": false,
            "description": "Only models with downloadable weights.",
            "type": "boolean"
          }
        },
        "type": "object"
      },
      "name": "get_leaderboard"
    },
    {
      "description": "One model's BenchLeader profile: Index and rank, category scores, list price, speed, latency, context window, its other reasoning-effort configurations, and its strongest independent benchmark results (each with its board rank, publisher and source link).",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "effort": {
            "description": "Reasoning-effort configuration to show (none, low, medium, high, xhigh, max…). Defaults to the best-ranked one.",
            "type": "string"
          },
          "model": {
            "description": "Model id (\"claude-opus-5-5\"), configuration id (\"gpt-6-astra@max\"), page URL or name.",
            "type": "string"
          },
          "results_limit": {
            "default": 10,
            "description": "How many benchmark results to return (at most 50).",
            "maximum": 50,
            "minimum": 1,
            "type": "integer"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "get_model"
    },
    {
      "description": "The benchmarks BenchLeader reads: what each measures, publisher, category, whether it feeds the Index (and its weight), how many models it covers, status and caveats. Filter by category or a search query. Paged.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "category": {
            "description": "Only this category, e.g. coding, agentic, reasoning, math, knowledge.",
            "type": "string"
          },
          "in_index_only": {
            "default": false,
            "description": "Only benchmarks that feed the BenchLeader Index.",
            "type": "boolean"
          },
          "limit": {
            "default": 50,
            "description": "How many benchmarks to return (at most 100).",
            "maximum": 100,
            "minimum": 1,
            "type": "integer"
          },
          "offset": {
            "default": 0,
            "description": "Rows to skip, for paging (use next_offset from the previous page).",
            "minimum": 0,
            "type": "integer"
          },
          "query": {
            "description": "Search benchmark names, ids, aliases and publishers (\"swe-bench\", \"arc\", \"epoch\").",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_benchmarks"
    },
    {
      "description": "Find models by name, alias, id or developer (\"opus\", \"gemini 4\", \"deepseek\"). Returns each match's id, rank, Index and reasoning-effort configurations, for use with get_model and compare_models.",
      "inputSchema": {
        "additionalProperties": false,
        "properties": {
          "limit": {
            "default": 10,
            "description": "How many matches to return (at most 25).",
            "maximum": 25,
            "minimum": 1,
            "type": "integer"
          },
          "query": {
            "description": "Model name, alias, id or developer.",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_models"
    }
  ]
}

What the leaf hashes

{"body":"9f8f1e6f7373d3f2080c298cc5e062df6becbde501450239a12d6e6dc3fb6cf3","id":1734419,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793504501877421,"prev":null,"subject":"fbee10ff-7e5b-477b-8542-9ad59b5f3f16","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-11-01 (302406 rows).

1. 0xc74c0534e9969b1dd6fcb15b40a786fa14f2eec476d78a8a2f7aa532e86492f2
2. 0xdaebfe3b8a690074ba0e9b62d59fd74a3a5b9c34a96cc79f030dde8a44ef22f1
3. 0xd7b2636006a08edb5b7bf1733b17471ea3bec82d9cee00b294d5902ee3c4ae13
4. 0xabc0d0ba0fdc45c6522e0ba21ca710fcc417309954f75f471b5a83fa24bd1d5a
5. 0x01133710a3aac21d44ac0f9e3cf7d6519c14307eab9ec120683d52b9ec3b5906
6. 0x36f14eb57f12f4f02bbb04a74d1a93fe19b850f465fb92304aac8028b6d247fe
7. 0xf1c7c8f26e9bc11be7514af32951772d71eeb8af5cd293a7938d684b6950f005
8. 0xf406a9314673acec6e0120eea5f2665758bbbd8c57c5a669dd94dd050586afb5
9. 0xa4ec9887198be6708ac25be015cff48493057208b3a80ccac4db5f88bdae6cdf
10. 0x9167a0f21d2816b2985abccc4200aab424cba360812b1a7cc342deba9abeed98
11. 0xe8a856eebf53bf70197cfc160e186ce58f4c845ebc7277885c2f524a6854b1e0
12. 0x708edbbc5c93eaadcb16f46d00180d1abd9f006f6897baa185b89bb0db26849f
13. 0xe14f0d8e2b9967bfb142a635a58f2d35462fc1282dcc137d3d835cfd908c00b2
14. 0x5da52d6bfc8f88d79ebced4b6bebec468f5c2d8a21c193d44e901c7a6ce7941e
15. 0x537331ef190eaefb4419f2a4558b952aaf9435d759df0b0c118b7df609ec1687
16. 0xfc183bee85dc11a067fb710c6eb88824b94a516ddbdf2717b839e672a2206a7e
17. 0xb5916fb7a3e87dc0702e46eeadcd22652e2e1e755f8d429cc7a14a67a350b51b
18. 0x6142ac48fda269c17791c79da99c2456ac6acfe98268f4d168a404fd6040c703
19. 0x3315fd2757fdd435852cc277377234a3f3909a6d2a089d0e36f6d59aacfda910

Day root

0x7fa2cba1cf3d6b35630896f5fe1a650adb307ea2c376e80a5f2d9276b7cb5ab3

Chained

0x577ff89ba012beeff3197bcff7fa86752074bdf54205a24359cc437be2a952a4

Published

On Arc Testnet, block 70262758: 0x435bc1b9331471d72e1998f2e420983b5189d4da65ffbd6f27ef40daf5e1ea90