{
  "arms": [
    {
      "arm": "cbm",
      "index_kind": "mcp",
      "index_tools": {
        "mcp__codebase-memory-mcp__get_architecture": 72,
        "mcp__codebase-memory-mcp__get_code_snippet": 718,
        "mcp__codebase-memory-mcp__query_graph": 654,
        "mcp__codebase-memory-mcp__search_code": 1950,
        "mcp__codebase-memory-mcp__search_graph": 1399,
        "mcp__codebase-memory-mcp__trace_path": 494
      },
      "setup_tools_excluded": {
        "mcp__codebase-memory-mcp__get_graph_schema": 66,
        "mcp__codebase-memory-mcp__index_repository": 615,
        "mcp__codebase-memory-mcp__index_status": 264,
        "mcp__codebase-memory-mcp__list_projects": 1012
      }
    },
    {
      "arm": "cg-ask-fz-009",
      "index_kind": "none",
      "index_tools": {},
      "setup_tools_excluded": {}
    },
    {
      "arm": "codegraph",
      "index_kind": "mcp",
      "index_tools": {
        "mcp__codegraph__codegraph_explore": 3599
      },
      "setup_tools_excluded": {}
    },
    {
      "arm": "codex",
      "index_kind": "none",
      "index_tools": {},
      "setup_tools_excluded": {}
    },
    {
      "arm": "cold",
      "index_kind": "none",
      "index_tools": {},
      "setup_tools_excluded": {}
    },
    {
      "arm": "cursor",
      "index_kind": "none",
      "index_tools": {},
      "setup_tools_excluded": {}
    },
    {
      "arm": "gitnexus",
      "index_kind": "mcp",
      "index_tools": {
        "Skill": 3,
        "mcp__gitnexus__context": 1033,
        "mcp__gitnexus__cypher": 605,
        "mcp__gitnexus__impact": 159,
        "mcp__gitnexus__list_repos": 23,
        "mcp__gitnexus__query": 1347,
        "mcp__gitnexus__route_map": 31,
        "mcp__gitnexus__tool_map": 16,
        "mcp__gitnexus__trace": 67
      },
      "setup_tools_excluded": {}
    },
    {
      "arm": "graphify",
      "index_kind": "skill",
      "index_tools": {
        "Skill": 520
      },
      "setup_tools_excluded": {}
    },
    {
      "arm": "serena",
      "index_kind": "mcp",
      "index_tools": {
        "mcp__serena__find_referencing_symbols": 6,
        "mcp__serena__find_symbol": 63,
        "mcp__serena__get_symbols_overview": 9
      },
      "setup_tools_excluded": {
        "mcp__serena__activate_project": 117,
        "mcp__serena__get_current_config": 16,
        "mcp__serena__initial_instructions": 229
      }
    }
  ],
  "definition": {
    "conversations": "a run; for MultiTurn one conversation carries the whole battery, so conversations_with_index counts a conversation once if any of its questions used the index",
    "grain": "one row per arm × model × exam × battery over the valid, scored runs of the ZeroShot and MultiTurn protocols; HumanExam is whole-battery and has no per-question tool attribution",
    "index_use": "a question run counts as using the index when at least one main-thread tool call is an index call: a Corograph query for Corograph; a call to an installed tool's own MCP surface, excluding its setup calls (listed per arm under setup_tools_excluded); a Skill invocation for a tool that ships as a skill",
    "threads": "main thread only — MCP tools are not offered to sub-agent threads"
  },
  "rows": [
    {
      "arm": "cbm",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 16,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "cbm",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 4,
      "questions_without_tools": 2,
      "index_calls": 19,
      "setup_calls": 12,
      "conversations": 5,
      "conversations_with_index": 4
    },
    {
      "arm": "cbm",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 25,
      "questions_without_tools": 0,
      "index_calls": 49,
      "setup_calls": 134,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "cbm",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 240,
      "questions_with_index": 88,
      "questions_without_tools": 11,
      "index_calls": 128,
      "setup_calls": 13,
      "conversations": 8,
      "conversations_with_index": 8
    },
    {
      "arm": "cbm",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 160,
      "questions_with_index": 145,
      "questions_without_tools": 3,
      "index_calls": 637,
      "setup_calls": 18,
      "conversations": 8,
      "conversations_with_index": 8
    },
    {
      "arm": "cbm",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 280,
      "questions_without_tools": 0,
      "index_calls": 1723,
      "setup_calls": 445,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 199,
      "questions_without_tools": 0,
      "index_calls": 1891,
      "setup_calls": 334,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 44,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 2,
      "questions_without_tools": 24,
      "index_calls": 4,
      "setup_calls": 8,
      "conversations": 10,
      "conversations_with_index": 2
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 97,
      "questions_without_tools": 0,
      "index_calls": 146,
      "setup_calls": 100,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 47,
      "questions_without_tools": 0,
      "index_calls": 167,
      "setup_calls": 144,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 5,
      "questions_without_tools": 18,
      "index_calls": 5,
      "setup_calls": 2,
      "conversations": 10,
      "conversations_with_index": 5
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 8,
      "questions_without_tools": 2,
      "index_calls": 48,
      "setup_calls": 21,
      "conversations": 10,
      "conversations_with_index": 8
    },
    {
      "arm": "cbm",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 14,
      "questions_without_tools": 0,
      "index_calls": 95,
      "setup_calls": 209,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 2,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cbm",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 4,
      "questions_without_tools": 0,
      "index_calls": 13,
      "setup_calls": 16,
      "conversations": 10,
      "conversations_with_index": 4
    },
    {
      "arm": "cbm",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 2,
      "questions_without_tools": 0,
      "index_calls": 3,
      "setup_calls": 131,
      "conversations": 10,
      "conversations_with_index": 2
    },
    {
      "arm": "cbm",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 11,
      "questions_without_tools": 0,
      "index_calls": 47,
      "setup_calls": 176,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cbm",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 21,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cbm",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 11,
      "questions_without_tools": 5,
      "index_calls": 77,
      "setup_calls": 25,
      "conversations": 10,
      "conversations_with_index": 8
    },
    {
      "arm": "cbm",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 17,
      "questions_without_tools": 0,
      "index_calls": 25,
      "setup_calls": 79,
      "conversations": 10,
      "conversations_with_index": 9
    },
    {
      "arm": "cbm",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 31,
      "questions_without_tools": 0,
      "index_calls": 210,
      "setup_calls": 90,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 150,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 180,
      "questions_with_index": 0,
      "questions_without_tools": 180,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 6,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 180,
      "questions_with_index": 0,
      "questions_without_tools": 180,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 9,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 300,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cg-ask-fz-009",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 200,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codegraph",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 18,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "codegraph",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 20,
      "questions_without_tools": 4,
      "index_calls": 20,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "codegraph",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 83,
      "questions_without_tools": 0,
      "index_calls": 111,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "codegraph",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 270,
      "questions_with_index": 67,
      "questions_without_tools": 47,
      "index_calls": 92,
      "setup_calls": 0,
      "conversations": 9,
      "conversations_with_index": 9
    },
    {
      "arm": "codegraph",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 180,
      "questions_with_index": 91,
      "questions_without_tools": 16,
      "index_calls": 159,
      "setup_calls": 0,
      "conversations": 9,
      "conversations_with_index": 9
    },
    {
      "arm": "codegraph",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 297,
      "questions_without_tools": 0,
      "index_calls": 593,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 199,
      "questions_without_tools": 0,
      "index_calls": 559,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 63,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 62,
      "questions_without_tools": 42,
      "index_calls": 66,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 156,
      "questions_without_tools": 38,
      "index_calls": 230,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 125,
      "questions_without_tools": 9,
      "index_calls": 228,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 3,
      "questions_without_tools": 33,
      "index_calls": 3,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 3
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 68,
      "questions_without_tools": 0,
      "index_calls": 73,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 153,
      "questions_without_tools": 0,
      "index_calls": 227,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 3,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 16,
      "questions_without_tools": 0,
      "index_calls": 16,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 7
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 181,
      "questions_without_tools": 0,
      "index_calls": 198,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 136,
      "questions_without_tools": 0,
      "index_calls": 164,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 1,
      "questions_without_tools": 40,
      "index_calls": 1,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 1
    },
    {
      "arm": "codegraph",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 90,
      "questions_without_tools": 9,
      "index_calls": 128,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 225,
      "questions_without_tools": 0,
      "index_calls": 373,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codegraph",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 148,
      "questions_without_tools": 0,
      "index_calls": 358,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 1,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 2,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 3,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 6,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 1,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 1,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 6,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "codex",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 16,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 0,
      "questions_without_tools": 3,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 240,
      "questions_with_index": 0,
      "questions_without_tools": 17,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 160,
      "questions_with_index": 0,
      "questions_without_tools": 20,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 36,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 24,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 24,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 4,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 3,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 21,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 20,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cold",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 152,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 13,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 15,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "composer-2.5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "composer-2.5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "composer-2.5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "composer-2.5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 51,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-luna",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 9,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-luna",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 62,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-sol",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 11,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-sol",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 37,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-terra",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 10,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "gpt-5.6-terra",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "grok-4.6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 1,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "grok-4.6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "grok-4.6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "cursor",
      "model": "grok-4.6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "gitnexus",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 5,
      "questions_without_tools": 13,
      "index_calls": 5,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 3
    },
    {
      "arm": "gitnexus",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 7,
      "questions_without_tools": 1,
      "index_calls": 17,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "gitnexus",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 39,
      "questions_without_tools": 0,
      "index_calls": 55,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "gitnexus",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 240,
      "questions_with_index": 8,
      "questions_without_tools": 24,
      "index_calls": 12,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 5
    },
    {
      "arm": "gitnexus",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 160,
      "questions_with_index": 43,
      "questions_without_tools": 2,
      "index_calls": 111,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 8
    },
    {
      "arm": "gitnexus",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 185,
      "questions_without_tools": 0,
      "index_calls": 517,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 152,
      "questions_without_tools": 0,
      "index_calls": 702,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 38,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 33,
      "questions_without_tools": 20,
      "index_calls": 55,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 179,
      "questions_without_tools": 0,
      "index_calls": 242,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 132,
      "questions_without_tools": 0,
      "index_calls": 303,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 19,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 17,
      "questions_without_tools": 1,
      "index_calls": 41,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 64,
      "questions_without_tools": 0,
      "index_calls": 186,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 5,
      "questions_without_tools": 0,
      "index_calls": 5,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 4
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 21,
      "questions_without_tools": 0,
      "index_calls": 53,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 9
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 104,
      "questions_without_tools": 0,
      "index_calls": 126,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 70,
      "questions_without_tools": 0,
      "index_calls": 135,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 14,
      "questions_without_tools": 13,
      "index_calls": 18,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 8
    },
    {
      "arm": "gitnexus",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 46,
      "questions_without_tools": 5,
      "index_calls": 107,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 143,
      "questions_without_tools": 0,
      "index_calls": 235,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "gitnexus",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 119,
      "questions_without_tools": 1,
      "index_calls": 359,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "graphify",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 2,
      "questions_without_tools": 11,
      "index_calls": 2,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 2
    },
    {
      "arm": "graphify",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 9,
      "questions_without_tools": 3,
      "index_calls": 9,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "graphify",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 131,
      "questions_without_tools": 0,
      "index_calls": 131,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 5
    },
    {
      "arm": "graphify",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 240,
      "questions_with_index": 0,
      "questions_without_tools": 32,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 160,
      "questions_with_index": 0,
      "questions_without_tools": 44,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 8,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 7,
      "questions_without_tools": 0,
      "index_calls": 7,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 6
    },
    {
      "arm": "graphify",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 15,
      "questions_without_tools": 0,
      "index_calls": 15,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 39,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 30,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 1,
      "questions_without_tools": 15,
      "index_calls": 1,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 1
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 3,
      "questions_without_tools": 4,
      "index_calls": 3,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 3
    },
    {
      "arm": "graphify",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 83,
      "questions_without_tools": 0,
      "index_calls": 83,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "graphify",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 2,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 13,
      "questions_without_tools": 0,
      "index_calls": 13,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 7
    },
    {
      "arm": "graphify",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 17,
      "questions_without_tools": 0,
      "index_calls": 17,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 9
    },
    {
      "arm": "graphify",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 24,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 18,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "graphify",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 161,
      "questions_without_tools": 0,
      "index_calls": 161,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "graphify",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 78,
      "questions_without_tools": 0,
      "index_calls": 78,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "serena",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 11,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-fable-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 100,
      "questions_with_index": 0,
      "questions_without_tools": 3,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 150,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 5,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-fable-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 80,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 4,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 270,
      "questions_with_index": 0,
      "questions_without_tools": 7,
      "index_calls": 0,
      "setup_calls": 1,
      "conversations": 9,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-haiku-4-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 180,
      "questions_with_index": 1,
      "questions_without_tools": 8,
      "index_calls": 1,
      "setup_calls": 3,
      "conversations": 9,
      "conversations_with_index": 1
    },
    {
      "arm": "serena",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 33,
      "questions_without_tools": 0,
      "index_calls": 39,
      "setup_calls": 134,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "serena",
      "model": "claude-haiku-4-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 30,
      "questions_without_tools": 0,
      "index_calls": 31,
      "setup_calls": 124,
      "conversations": 10,
      "conversations_with_index": 10
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 40,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-6",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 23,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 53,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-6",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 1,
      "questions_without_tools": 0,
      "index_calls": 3,
      "setup_calls": 44,
      "conversations": 10,
      "conversations_with_index": 1
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 28,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-8",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 6,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-4-8",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 1,
      "questions_without_tools": 0,
      "index_calls": 1,
      "setup_calls": 1,
      "conversations": 10,
      "conversations_with_index": 1
    },
    {
      "arm": "serena",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 1,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 1,
      "questions_without_tools": 0,
      "index_calls": 2,
      "setup_calls": 1,
      "conversations": 10,
      "conversations_with_index": 1
    },
    {
      "arm": "serena",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-opus-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 25,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-sonnet-5",
      "exam": "MultiTurnExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 0,
      "questions_without_tools": 4,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos",
      "questions": 300,
      "questions_with_index": 0,
      "questions_without_tools": 0,
      "index_calls": 0,
      "setup_calls": 0,
      "conversations": 10,
      "conversations_with_index": 0
    },
    {
      "arm": "serena",
      "model": "claude-sonnet-5",
      "exam": "ZeroShotExam",
      "battery": "memos-hard",
      "questions": 200,
      "questions_with_index": 1,
      "questions_without_tools": 0,
      "index_calls": 1,
      "setup_calls": 1,
      "conversations": 10,
      "conversations_with_index": 1
    }
  ]
}
