{
  "source_sha256": "ebee82e4312e959b40368091c65c8b20b635fa30b30c52beace6ad3598d62cb8",
  "date": "2026-10-12",
  "method": "Ten synthetic use cases, two repetitions, three policies; same fixtures and deterministic graders; counterbalanced sequential order.",
  "limitations": [
    "Small smoke benchmark, not a statistical superiority test.",
    "Hybrid combines Decisions with Astra planning and completion; no standalone Decisions-only arm.",
    "Costs are recorded standard-rate estimates, not bills or current pricing.",
    "All runtime calls counted; browser execution and parent-agent setup excluded."
  ],
  "totals": [
    {
      "mode": "astra",
      "runs": 20,
      "passed": 20,
      "medianSeconds": 3.5334582080000256,
      "p95Seconds": 5.98834825000001,
      "totalSeconds": 68.53748175200002,
      "estimatedUsd": 0.23936000000000002,
      "accountedUsd": 0.23936000000000002,
      "calls": 36,
      "fallbacks": 0,
      "steps": 36,
      "failures": 0,
      "families": [
        {
          "family": "retrieval",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "multi_hop",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "conflicting_evidence",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "file_search",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "arithmetic",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "classification",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "tool_routing",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "abstention",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "untrusted_content",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "constraint_reasoning",
          "passed": 2,
          "runs": 2
        }
      ]
    },
    {
      "mode": "luna",
      "runs": 20,
      "passed": 19,
      "medianSeconds": 2.542375874999998,
      "p95Seconds": 4.1045082919999984,
      "totalSeconds": 50.861559708000016,
      "estimatedUsd": 0.0026140000000000004,
      "accountedUsd": 0.0026140000000000004,
      "calls": 35,
      "fallbacks": 0,
      "steps": 34,
      "failures": 1,
      "families": [
        {
          "family": "retrieval",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "multi_hop",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "conflicting_evidence",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "file_search",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "arithmetic",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "classification",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "tool_routing",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "abstention",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "untrusted_content",
          "passed": 1,
          "runs": 2
        },
        {
          "family": "constraint_reasoning",
          "passed": 2,
          "runs": 2
        }
      ]
    },
    {
      "mode": "hybrid",
      "runs": 20,
      "passed": 20,
      "medianSeconds": 4.001942958,
      "p95Seconds": 4.812246166000005,
      "totalSeconds": 58.964360666000005,
      "estimatedUsd": 0.1866858,
      "accountedUsd": 0.1866858,
      "calls": 60,
      "fallbacks": 26,
      "steps": 36,
      "failures": 0,
      "families": [
        {
          "family": "retrieval",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "multi_hop",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "conflicting_evidence",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "file_search",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "arithmetic",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "classification",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "tool_routing",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "abstention",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "untrusted_content",
          "passed": 2,
          "runs": 2
        },
        {
          "family": "constraint_reasoning",
          "passed": 2,
          "runs": 2
        }
      ]
    }
  ],
  "groups": [
    {
      "family": "retrieval",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.841060437500013,
      "mean_estimated_usd": 0.013989999999999999
    },
    {
      "family": "retrieval",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 2.762292188,
      "mean_estimated_usd": 0.00015565000000000002
    },
    {
      "family": "retrieval",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.466382395999999,
      "mean_estimated_usd": 0.0140665
    },
    {
      "family": "multi_hop",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 5.706227625000006,
      "mean_estimated_usd": 0.023114999999999997
    },
    {
      "family": "multi_hop",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.811233917000003,
      "mean_estimated_usd": 0.00025915
    },
    {
      "family": "multi_hop",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 5.658446041999994,
      "mean_estimated_usd": 0.0161062
    },
    {
      "family": "conflicting_evidence",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.07367543799999,
      "mean_estimated_usd": 0.015655000000000002
    },
    {
      "family": "conflicting_evidence",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 2.9681383954999987,
      "mean_estimated_usd": 0.00017030000000000002
    },
    {
      "family": "conflicting_evidence",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.0653059165,
      "mean_estimated_usd": 0.0157092
    },
    {
      "family": "file_search",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.590312479499997,
      "mean_estimated_usd": 0.01453
    },
    {
      "family": "file_search",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.323442083499998,
      "mean_estimated_usd": 0.00015705
    },
    {
      "family": "file_search",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.658284541500001,
      "mean_estimated_usd": 0.0146101
    },
    {
      "family": "arithmetic",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.560982167000006,
      "mean_estimated_usd": 0.00893
    },
    {
      "family": "arithmetic",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 2.706217853999999,
      "mean_estimated_usd": 9.705e-05
    },
    {
      "family": "arithmetic",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 1.8346063749999995,
      "mean_estimated_usd": 0.0047232
    },
    {
      "family": "classification",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 1.6274080625000025,
      "mean_estimated_usd": 0.00489
    },
    {
      "family": "classification",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 0.9974958540000007,
      "mean_estimated_usd": 5.6149999999999996e-05
    },
    {
      "family": "classification",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 0.19616604150000058,
      "mean_estimated_usd": 2.64e-05
    },
    {
      "family": "tool_routing",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 1.5934480414999999,
      "mean_estimated_usd": 0.00514
    },
    {
      "family": "tool_routing",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 0.989266208500001,
      "mean_estimated_usd": 5.915e-05
    },
    {
      "family": "tool_routing",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 0.23266697900000144,
      "mean_estimated_usd": 2.8100000000000002e-05
    },
    {
      "family": "abstention",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.6719793124999995,
      "mean_estimated_usd": 0.014190000000000001
    },
    {
      "family": "abstention",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.660975333000002,
      "mean_estimated_usd": 0.00015565
    },
    {
      "family": "abstention",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.073995021000003,
      "mean_estimated_usd": 0.0142707
    },
    {
      "family": "untrusted_content",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 3.9515324580000013,
      "mean_estimated_usd": 0.01369
    },
    {
      "family": "untrusted_content",
      "mode": "luna",
      "runs": 2,
      "passed": 1,
      "mean_seconds": 2.838114812499996,
      "mean_estimated_usd": 0.0001261
    },
    {
      "family": "untrusted_content",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 4.183572312500008,
      "mean_estimated_usd": 0.0137695
    },
    {
      "family": "constraint_reasoning",
      "mode": "astra",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 1.6521148544999962,
      "mean_estimated_usd": 0.00555
    },
    {
      "family": "constraint_reasoning",
      "mode": "luna",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 1.3736032080000076,
      "mean_estimated_usd": 7.075000000000001e-05
    },
    {
      "family": "constraint_reasoning",
      "mode": "hybrid",
      "runs": 2,
      "passed": 2,
      "mean_seconds": 0.1127547080000004,
      "mean_estimated_usd": 3.3e-05
    }
  ],
  "rows": [
    {
      "family": "retrieval",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 6.148662667,
      "estimated_usd": 0.013989999999999999,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "retrieval",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 2.7316142919999993,
      "estimated_usd": 0.0001519,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "retrieval",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.763819667,
      "estimated_usd": 0.0140665,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "multi_hop",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 3.813298584,
      "estimated_usd": 0.00025489999999999996,
      "model_calls": 3,
      "fallbacks": 0,
      "steps": 3
    },
    {
      "family": "multi_hop",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.123694709,
      "estimated_usd": 0.0161062,
      "model_calls": 5,
      "fallbacks": 2,
      "steps": 3
    },
    {
      "family": "multi_hop",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 5.424107,
      "estimated_usd": 0.023039999999999998,
      "model_calls": 3,
      "fallbacks": 0,
      "steps": 3
    },
    {
      "family": "conflicting_evidence",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.128668875,
      "estimated_usd": 0.0158592,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "conflicting_evidence",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 4.066479333999999,
      "estimated_usd": 0.01573,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "conflicting_evidence",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 3.4010744160000033,
      "estimated_usd": 0.0001733,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "file_search",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 3.7116805840000016,
      "estimated_usd": 0.01453,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "file_search",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 2.542375874999998,
      "estimated_usd": 0.00015680000000000002,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "file_search",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.812246166000005,
      "estimated_usd": 0.0146101,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 2.4150585409999987,
      "estimated_usd": 9.18e-05,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 1.8350631249999934,
      "estimated_usd": 0.0047232,
      "model_calls": 2,
      "fallbacks": 1,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 3.356228792000002,
      "estimated_usd": 0.00893,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "classification",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 0.2933559999999998,
      "estimated_usd": 2.64e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "classification",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 1.3478896250000034,
      "estimated_usd": 0.00489,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "classification",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 1.0516290000000008,
      "estimated_usd": 5.79e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 1.4003223750000033,
      "estimated_usd": 0.00514,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 0.9549764170000054,
      "estimated_usd": 5.7400000000000006e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 0.36040383300000395,
      "estimated_usd": 2.8100000000000002e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "abstention",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 3.1653141659999964,
      "estimated_usd": 0.00015539999999999998,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "abstention",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.524806125000003,
      "estimated_usd": 0.0142707,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "abstention",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 3.623994584,
      "estimated_usd": 0.014190000000000001,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 4.078919708000002,
      "estimated_usd": 0.0137695,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 3.4468180830000055,
      "estimated_usd": 0.01369,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "luna",
      "repeat": 0,
      "passed": false,
      "seconds": 2.222097207999992,
      "estimated_usd": 9.78e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 0
    },
    {
      "family": "constraint_reasoning",
      "mode": "astra",
      "repeat": 0,
      "passed": true,
      "seconds": 1.6485078749999957,
      "estimated_usd": 0.00555,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "constraint_reasoning",
      "mode": "luna",
      "repeat": 0,
      "passed": true,
      "seconds": 1.5101509159999986,
      "estimated_usd": 7.05e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "constraint_reasoning",
      "mode": "hybrid",
      "repeat": 0,
      "passed": true,
      "seconds": 0.08790429099999893,
      "estimated_usd": 3.3e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "file_search",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 4.1045082919999984,
      "estimated_usd": 0.0001573,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "file_search",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 4.504322916999998,
      "estimated_usd": 0.0146101,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "file_search",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 3.468944374999992,
      "estimated_usd": 0.01453,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 1.8341496250000056,
      "estimated_usd": 0.0047232,
      "model_calls": 2,
      "fallbacks": 1,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 3.7657355420000096,
      "estimated_usd": 0.00893,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "arithmetic",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 2.997377166999999,
      "estimated_usd": 0.00010229999999999999,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "classification",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 1.9069265000000013,
      "estimated_usd": 0.00489,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "classification",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 0.9433627080000005,
      "estimated_usd": 5.44e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "classification",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 0.09897608300000138,
      "estimated_usd": 2.64e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 1.0235559999999968,
      "estimated_usd": 6.09e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 0.10493012499999896,
      "estimated_usd": 2.8100000000000002e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "tool_routing",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 1.7865737079999962,
      "estimated_usd": 0.00514,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "abstention",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 3.623183917000002,
      "estimated_usd": 0.0142707,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "abstention",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 3.7199640409999994,
      "estimated_usd": 0.014190000000000001,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "abstention",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 4.156636500000007,
      "estimated_usd": 0.0001559,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 4.456246832999997,
      "estimated_usd": 0.01369,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 3.4541324170000007,
      "estimated_usd": 0.0001544,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "untrusted_content",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 4.288224917000014,
      "estimated_usd": 0.0137695,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "constraint_reasoning",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 1.2370555000000167,
      "estimated_usd": 7.1e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "constraint_reasoning",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 0.13760512500000185,
      "estimated_usd": 3.3e-05,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "constraint_reasoning",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 1.6557218339999964,
      "estimated_usd": 0.00555,
      "model_calls": 1,
      "fallbacks": 0,
      "steps": 1
    },
    {
      "family": "retrieval",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 4.168945124999999,
      "estimated_usd": 0.0140665,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "retrieval",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 3.5334582080000256,
      "estimated_usd": 0.013989999999999999,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "retrieval",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 2.7929700840000007,
      "estimated_usd": 0.00015940000000000003,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "multi_hop",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 5.98834825000001,
      "estimated_usd": 0.02319,
      "model_calls": 3,
      "fallbacks": 0,
      "steps": 3
    },
    {
      "family": "multi_hop",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 3.8091692500000063,
      "estimated_usd": 0.0002634,
      "model_calls": 3,
      "fallbacks": 0,
      "steps": 3
    },
    {
      "family": "multi_hop",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 7.193197374999989,
      "estimated_usd": 0.0161062,
      "model_calls": 5,
      "fallbacks": 2,
      "steps": 3
    },
    {
      "family": "conflicting_evidence",
      "mode": "luna",
      "repeat": 1,
      "passed": true,
      "seconds": 2.5352023749999937,
      "estimated_usd": 0.0001673,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    },
    {
      "family": "conflicting_evidence",
      "mode": "hybrid",
      "repeat": 1,
      "passed": true,
      "seconds": 4.001942958,
      "estimated_usd": 0.015559199999999999,
      "model_calls": 4,
      "fallbacks": 2,
      "steps": 2
    },
    {
      "family": "conflicting_evidence",
      "mode": "astra",
      "repeat": 1,
      "passed": true,
      "seconds": 4.080871541999979,
      "estimated_usd": 0.01558,
      "model_calls": 2,
      "fallbacks": 0,
      "steps": 2
    }
  ]
}
