{
  "prepared_on": "2026-10-23",
  "scope": "Saved real-agent runs only; no tuning, API calls, or rescoring.",
  "score_field": "success_rate_6",
  "seeds": [
    42,
    123,
    2024
  ],
  "model_order": [
    "gpt-5.4-mini",
    "gpt-5.4-nano",
    "gpt-4o-mini",
    "gpt-4.1-nano",
    "groq-gpt-oss-120b"
  ],
  "modules": {
    "MPC": {
      "batch": "2026-10-18_12h",
      "timestamp_meaning": "Archive organization time, not original run date.",
      "records": 135,
      "cases": [
        "AUV.json",
        "AircraftPitch.json",
        "BallBeam.json",
        "CSTR.json",
        "CartPole.json",
        "DCMotor.json",
        "InvPendulum.json",
        "QuanserHelicopter.json",
        "TwoLinkManipulator.json"
      ],
      "n_seeds_per_case_model": 3,
      "cost_and_success": [
        {
          "model": "gpt-5.4-mini",
          "n": 27,
          "success": 0.7099380000000001,
          "cost": 0.032723555555555554
        },
        {
          "model": "gpt-5.4-nano",
          "n": 27,
          "success": 0.7489934074074073,
          "cost": 0.01475603703703704
        },
        {
          "model": "gpt-4o-mini",
          "n": 27,
          "success": 0.720589037037037,
          "cost": 0.010708805555555555
        },
        {
          "model": "gpt-4.1-nano",
          "n": 27,
          "success": 0.8142885925925926,
          "cost": 0.003771503703703704
        },
        {
          "model": "groq-gpt-oss-120b",
          "n": 27,
          "success": 0.4440645925925925,
          "cost": 0.00026231074074074075
        }
      ],
      "source_bar_figure": "benchmarks/MPC/plots/2026-10-18_12h/dashboard/seed_statistics/success_rate_6_seed_statistics.png",
      "source_bar_sha256": "003ae8fdd798a5630747600f7643807895f89b8ba4fb05f448287221dfeac6bb",
      "copied_bar_sha256": "003ae8fdd798a5630747600f7643807895f89b8ba4fb05f448287221dfeac6bb",
      "example": {
        "json": "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/AUV_results.json",
        "json_sha256": "2e817385608d47cae3a19b0045da6f7175689e86c7c65483bf4a3db690c66551",
        "trajectory": "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/trajectories/AUV_test_1_verification.npz",
        "trajectory_sha256": "082c3970281e2f926d2a9a6db1e02425aedc756f68aaa603ec5997c6d2c0b593",
        "samples": 961,
        "recorded_duration_s": 19.2,
        "success_rate_6": 0.898398,
        "category_checks": {
          "mse_max": {
            "limit": [
              0.05
            ],
            "measured_value": [
              0.04058185967234461
            ],
            "comparison": "<=",
            "passed": true,
            "source": "verification.tracking_mse.full (each named controlled output)",
            "score": 0.9005202204227366,
            "outputs": [
              "depth"
            ],
            "per_output": {
              "depth": {
                "limit": 0.05,
                "measured_value": 0.04058185967234461,
                "passed": true,
                "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance.",
                "score": 0.9005202204227366
              }
            },
            "unavailable_outputs": [],
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "settling_time_max_s": {
            "limit": 4.0,
            "measured_value": 1.78,
            "comparison": "<=",
            "passed": true,
            "source": "verification.raw_result.metrics.settling_time, with settled=true",
            "settled": true,
            "score": 1.0,
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "overshoot_max_pct": {
            "limit": [
              5.0
            ],
            "measured_value": [
              1.6348473231316163
            ],
            "comparison": "<=",
            "passed": true,
            "source": "100 * verification.raw_result.metrics.per_state_overshoot (controlled states only)",
            "score": 1.0,
            "outputs": [
              "depth"
            ],
            "per_output": {
              "depth": {
                "limit": 5.0,
                "measured_value": 1.6348473231316163,
                "passed": true,
                "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance.",
                "score": 1.0
              }
            },
            "unavailable_outputs": [],
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "control_effort_max": {
            "limit": 0.0125,
            "measured_value": 0.016756146222603404,
            "comparison": "<=",
            "passed": false,
            "source": "verification.raw_result.metrics.control_effort (mean squared applied inputs)",
            "score": 0.6930721050278313,
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          }
        }
      },
      "score_parameters": {
        "half_credit_ratio": 2.0,
        "zero_limit_tolerances": {},
        "full_credit_fraction": 0.6
      },
      "source_reports_unchanged": true,
      "cases_by_model": {
        "AUV.json": {
          "gpt-5.4-mini": 0.880429,
          "gpt-5.4-nano": 0.8777966666666667,
          "gpt-4o-mini": 0.8911890000000001,
          "gpt-4.1-nano": 0.8927650000000001,
          "groq-gpt-oss-120b": 0.4330523333333334
        },
        "AircraftPitch.json": {
          "gpt-5.4-mini": 0.15102033333333334,
          "gpt-5.4-nano": 0.166758,
          "gpt-4o-mini": 0.0005210000000000001,
          "gpt-4.1-nano": 0.5461950000000001,
          "groq-gpt-oss-120b": 0.0009260000000000001
        },
        "BallBeam.json": {
          "gpt-5.4-mini": 0.8806263333333333,
          "gpt-5.4-nano": 0.9097993333333333,
          "gpt-4o-mini": 0.877031,
          "gpt-4.1-nano": 0.8992453333333333,
          "groq-gpt-oss-120b": 0.512666
        },
        "CSTR.json": {
          "gpt-5.4-mini": 0.5613006666666666,
          "gpt-5.4-nano": 0.6890700000000001,
          "gpt-4o-mini": 0.6606926666666667,
          "gpt-4.1-nano": 0.7487560000000001,
          "groq-gpt-oss-120b": 0.425251
        },
        "CartPole.json": {
          "gpt-5.4-mini": 0.5190816666666667,
          "gpt-5.4-nano": 0.5732970000000001,
          "gpt-4o-mini": 0.6123373333333334,
          "gpt-4.1-nano": 0.6044360000000001,
          "groq-gpt-oss-120b": 0.305288
        },
        "DCMotor.json": {
          "gpt-5.4-mini": 0.592765,
          "gpt-5.4-nano": 0.655735,
          "gpt-4o-mini": 0.596532,
          "gpt-4.1-nano": 0.6959209999999999,
          "groq-gpt-oss-120b": 1.0
        },
        "InvPendulum.json": {
          "gpt-5.4-mini": 0.9628776666666666,
          "gpt-5.4-nano": 0.961719,
          "gpt-4o-mini": 0.9772416666666667,
          "gpt-4.1-nano": 0.9581806666666667,
          "groq-gpt-oss-120b": 0.4303679999999999
        },
        "QuanserHelicopter.json": {
          "gpt-5.4-mini": 0.905493,
          "gpt-5.4-nano": 0.9292183333333334,
          "gpt-4o-mini": 0.9189316666666666,
          "gpt-4.1-nano": 0.9884186666666667,
          "groq-gpt-oss-120b": 0.507019
        },
        "TwoLinkManipulator.json": {
          "gpt-5.4-mini": 0.9358483333333334,
          "gpt-5.4-nano": 0.9775473333333333,
          "gpt-4o-mini": 0.950825,
          "gpt-4.1-nano": 0.9946796666666667,
          "groq-gpt-oss-120b": 0.38201100000000004
        }
      },
      "report_sha256": {
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/AircraftPitch_results.json": "afda611ab0effb75926324b61fca287cc48097f1c362288eaf4a6ae0febc33b9",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/AUV_results.json": "afbbd25b896f28fe3d52b4095a649c1da8e3b1db899cfb616c3fefbdd908c441",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/BallBeam_results.json": "dc0de26ab088d493e87d12828869ed36e95cadaa5f6de4ec2899fd76e2d75231",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/CartPole_results.json": "edee2e4f3ed129cc1a2deef28d15601086b4b30340eed396d1c7d48f93615dab",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/CSTR_results.json": "a9dce18c8efd7f6e202812fc2392e8b39295677db99b6dd916c2d5c14ed62368",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/DCMotor_results.json": "9b351bed28971359a6005f99f26273b2e180252d71fdb00cec181bcdac48fa34",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/InvPendulum_results.json": "65e2c9f3ff3eeb4c4f581e4d81d28eb5bc21b19c35f4a22b133f017fa777e8c7",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/QuanserHelicopter_results.json": "2cd522c5dd6376085995e0e4d1f5fb11db2a9b7f027f89de6777c209c138530e",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed42/TwoLinkManipulator_results.json": "eeb0aa7e1c88b56f83c2d2c024c75e9ca1c495988d45d0e667682ade46cc34c6",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/AircraftPitch_results.json": "f22f584d3437d2433fdc56738c96ae77615f40e5d111f9d279afebcd81092efa",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/AUV_results.json": "852d2c7f4d69583793593609d99d8655e9c8edfd222d9db2a03104f7305422c0",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/BallBeam_results.json": "23b3afc60c7d2016a374581bd0c0e92672a374887e93cad534966bc83d69fbdf",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/CartPole_results.json": "61ed80e6e76e2f407fa113a8ed49dd85c6ed51f85e674481ed3cb0ba2adc2529",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/CSTR_results.json": "37019d7c2d3fe0f8f46031c3437ea1ce879e389b0eac7669a09711641312ed92",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/DCMotor_results.json": "d7aa827b5aaaedb6f112552bcf88084f2c09f41565f2e3c50cf8d8b7d63bb394",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/InvPendulum_results.json": "ad091909be5fc4d7a7832534162c2b957d1512424de503aa628356fcbe9358f7",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/QuanserHelicopter_results.json": "d9f85ce81d9faba518ed8f816cd1b16f85c0c272ef59d4a4213001c8357e2764",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed123/TwoLinkManipulator_results.json": "233bede48eebbf3b1b145cef8f231fdc94dbd1cd3be7424c582303ecd935e048",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/AircraftPitch_results.json": "d63b05941467a767b679ec478ff7f3f343544ebde4e17512c43b2d2db81a2e48",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/AUV_results.json": "9e5049e8b71cf3127a6d82c72af1c22d7218406a675f0056a874a80cebcb2d16",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/BallBeam_results.json": "a8b82bb9d2d647338de851e953cbc13e4a621ddea89fddbfc954e0e2c1d626b6",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/CartPole_results.json": "f87f7d9784b0b1ddf56e2476d09a5de8943b66f7d3ad86981528fac2e2870bfa",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/CSTR_results.json": "c3c2860571c7dcd85c6858e87ad2414c6d09784f2e090fae8b77bdd88cc212de",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/DCMotor_results.json": "fea52ed1351bc9723f6d721399b90c2db82716ecf6852530c653a8a32552e99f",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/InvPendulum_results.json": "9b63ad1479b1356684e62e4e260bc6374f003c7d7aed3ae87a65f325f72a2719",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/QuanserHelicopter_results.json": "b0c480f433993e85e29f62bc5bc055ab58d5db7278ec0d84ed287c7896da2402",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-mini/seed2024/TwoLinkManipulator_results.json": "fe396579356a9899f699347250420e7a869d916b7b7e6fcfe0a01e25e553e8ff",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/AircraftPitch_results.json": "58ee97d1f9b9f573a15ad6ae246549d5b6ee51b82535bd22fdcb0e3fb3fe83ee",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/AUV_results.json": "3d5472d3798492c01c079a2f20b3b9378641adc28a2d6d4d9c14810a72dec4cc",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/BallBeam_results.json": "b8e5bd81288168e5c002a74af50882f1e91c2f57bf849d228728cb4a08782010",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/CartPole_results.json": "66a90d93d2afb7b9b329e8f7e7c1f2966417a60e2d25c06f0e72455873a29dc5",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/CSTR_results.json": "ad99ad371ee736ddf9d41542224a17af716db11c82aa3c63b0088a6952c29035",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/DCMotor_results.json": "eaba3af685a4b2c1b8cd1b75f7acb1d313ae16588656afa3c1c0c50f9e2dde9b",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/InvPendulum_results.json": "89eb67b492e7f0cf8dc27aa38c78cfc42ffff00a689c3f316b3951ef11317a80",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/QuanserHelicopter_results.json": "37e7b08744307924e04103f1e8a81bf88be048bb87e1b06a5bd39a7cf32509fb",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed42/TwoLinkManipulator_results.json": "52a705d0fdf5d4550d547f182d123ec9ee018b267a4acec00dfcf1d925aaedd0",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/AircraftPitch_results.json": "6d98b6341a3ac35fe7d5504453c6db3c5ae49cc610391bff24964925f3d237ff",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/AUV_results.json": "a53060286184e0dff8e4457d467890a506e6dc15fe6f5aba9bfc403aefa7224a",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/BallBeam_results.json": "70be650c746054cb75388a3ccdcab1cc3dffa0615ba7dcbb6ae7cd60c4da096d",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/CartPole_results.json": "007bde27c89147ddf2d8fbfb7f7d73a2a26030b1e656f1b76d46fdeea466dace",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/CSTR_results.json": "b75d0725330da06a831d145e04294bb2b38a21ac855221563bec24956aeab6dd",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/DCMotor_results.json": "1533a237b7f382e320465f8888288b7f2291e23574f1d24d1a19cd59b50d6929",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/InvPendulum_results.json": "50d9e1fd498498a4ef5880dd7d5da4aa26839e10542dc4f9ffd466c61092496b",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/QuanserHelicopter_results.json": "8ae4960fddf5937896d160ca492eb7d07eb277f154a9f34af6e68008b3eb64ca",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed123/TwoLinkManipulator_results.json": "17e175c0a739c9ad5832121f114737bb2fa450257fa41d0bdbe11cde4d3bb625",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/AircraftPitch_results.json": "f35ce3d20369fdc1e9c5be7a563ec455965a021f1c3053945cdf10edba4fa073",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/AUV_results.json": "97f625cb5f40e909b60a730537d428cc5aedbd2a3ec3e7bd305f0ad6900a3607",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/BallBeam_results.json": "5cdcfd29a02dc41403effec39a104a86aa62ac7621db380b21d1db6006c4e4dd",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/CartPole_results.json": "1f66ea9e76727b0a8b1d45faaf0c6a9ff234ef7fa460e7e883ff11bab7071455",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/CSTR_results.json": "996fcecd229a29154cc20e66b2343acce64a2e96a01bc557825fc04038ed320a",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/DCMotor_results.json": "f6ae23e3bf360f78971a2bacaff471764836103ec08ac966f5fb7dfc47a67cfb",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/InvPendulum_results.json": "712b968ddb5c81a9d40950ed804291675b8ee2acb7c312149e38f963d6ac84e2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/QuanserHelicopter_results.json": "d52e1c2ee60917f43fe8bab5ade0c4d810928b85ba2f1a1f5753228016356c13",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-5.4-nano/seed2024/TwoLinkManipulator_results.json": "0114848de6b9cf1df436009d97948a5666c128a3046271257d43d28989a5e5b1",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/AircraftPitch_results.json": "6b19f67459b16403f5455f38dfd8e074172aaa7870feca9952d715bb09d3bceb",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/AUV_results.json": "ab71228e4c2e4ec940775be02eab760d5172d00fec4532ea83e190bb4b60c752",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/BallBeam_results.json": "eb1659502a6a67fe843c1ea10ba6f29df420a36a12aa5c30105e890e96170333",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/CartPole_results.json": "4a714ccfc52480a7d05a060f99d743389ef516be1a091cf6e4259fe84382815c",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/CSTR_results.json": "428b619537c36bebfb0df7c3e5b02dbae06128d635a7455f524bd96c921f9a8a",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/DCMotor_results.json": "f86d93378121693888fd14e0c73cce4c1f97c8e93e6bbc2e90d86e1cc7d8d1fe",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/InvPendulum_results.json": "bc0529b41aa52e0f2e816f531147cdd8d2a838f4111ff9c3a8a7902d8107fa27",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/QuanserHelicopter_results.json": "d7772a293cba5c9be738f1f88c41cf2ad46faac595ede25338e3bfc9259aa89d",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed42/TwoLinkManipulator_results.json": "11916cce978dfd87150c705683028c9f460fcd2a50c9ddc89bf082c3a327f5f4",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/AircraftPitch_results.json": "a82217c7e79c4bf033f16c31f2e8af908bf205eeb1c90e6d17b6f1b28f8388cd",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/AUV_results.json": "287b4a77e9bf8f2e12d106583bec82b411ccb1d1e83e222ed261a08a90c562d4",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/BallBeam_results.json": "e59aeeb42dae9adcc59f26d9b44342481a9c5d737dde573f830e6b406adf6000",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/CartPole_results.json": "fcf984a22b7d247820aabda80f7e0bb4b26cf42879420d842af6bd31e0831fd5",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/CSTR_results.json": "35333e6a4d5340834adfd23d4d62cbdc6557d38d2a2ecb94b5bbd84e3d5a2583",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/DCMotor_results.json": "e120715626587dcfe3b4ae615610b0dcfb56fa37058b11fd2650b6309d485d30",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/InvPendulum_results.json": "94decfbbddaa26ed087dddf90758d7cd6dcfa6e0f2ca17ae4cbdd60ace80ab58",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/QuanserHelicopter_results.json": "2a6dff977486c2d28a7b3a8fa8a69dee2b259491c573bc3c72c8c636f98b4777",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed123/TwoLinkManipulator_results.json": "3bc5b15ac219ce2d0ae0673c7dc0fc47fa3d97b531cffcfb891f4f0f4779b3cd",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/AircraftPitch_results.json": "d5471eababebf3ebf802551c15482218666a70494d46c308c226f69468b74c90",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/AUV_results.json": "b30d31585e64998bbb4ddd276be9918ee537ddc5b5c31dccf8096394e250e1d3",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/BallBeam_results.json": "e91c5249092b64cb60608ae56aa2717cb4ceac76273b1e1b61b3979070a2d564",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/CartPole_results.json": "c861dcbb828631be7e2c29797a9ca0d5aafd95503a7d9cac14a858932ee209ee",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/CSTR_results.json": "04d87e5bd373a214e682fe7bf290b1b06fb1e8db80ed9995fc83835284b162e7",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/DCMotor_results.json": "4f5392c8e601c0647cae94987ff62fb9e6bc1d55b55d2ce231b01eaea98bd0e7",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/InvPendulum_results.json": "bbec57c99c576a5cd4aaec17420b853dd4e555d7b59413786af4eedbc5b3c204",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/QuanserHelicopter_results.json": "90cc9313e57ce9ac76d0b3694eab52d010adddd78879718f21d3a572981bba60",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4o-mini/seed2024/TwoLinkManipulator_results.json": "e7bbb52e48af4caab0a433a6844c9cad1cfa219997e9b071e8c550f58e5ca772",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/AircraftPitch_results.json": "09ecc938f240ded35aa37a9ad6209be7b3ab0e2601c2b133e53bda1b84512762",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/AUV_results.json": "2e817385608d47cae3a19b0045da6f7175689e86c7c65483bf4a3db690c66551",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/BallBeam_results.json": "3beda4114388519b4d1a901701741f8618a05a5232214309e0e9042a6ecf3901",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/CartPole_results.json": "ef75ad67770f9535b0e948b761625f4b23bfe45aa07d0a6ea459336fdb3fae00",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/CSTR_results.json": "e747fb55076f5c1376bfc89d0d330fb80b74bfc0a6732250d4531246a1eaf383",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/DCMotor_results.json": "514bdb498fe31967d33278dc9d042c672d080c4b663c473ed6c66b36f3f9da4c",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/InvPendulum_results.json": "a9b9e35cee7db8dd7a0b76f05880b8397d1dac4387ab38aee8c74a529c1d0a01",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/QuanserHelicopter_results.json": "d91d25cb1059bc170d6e7ae3c28255376a6d4692fdba7ca62d46018413f51cc0",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed42/TwoLinkManipulator_results.json": "62b7a91187327316093f781dea96ddee31fffec131945dc25877b6ded8458546",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/AircraftPitch_results.json": "86c2a4baeeebd230b21f55d346dd3c54bd3a6cac83cd84a70d7f5724cfad4a34",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/AUV_results.json": "78b20191d693a33dc5057881a72edf851d84d9b91835a9401e5fa37749243a17",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/BallBeam_results.json": "c084a11f2f43cf27bc12ca34eb259562db4bacd54a2a4d8a67736aeac2a3f6f7",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/CartPole_results.json": "7807fe4052013ef75baf91c816ba6497fb3a3673475941f40117d1f9172155b1",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/CSTR_results.json": "75378c74a9a1f449159606ddaa9f6bfb3d4934fd229280bd4fcd1a680f2be689",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/DCMotor_results.json": "efd99b69ae75de8426ee23419d0108538231065281bc760aee347a75b35424d2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/InvPendulum_results.json": "9bd68ca550aba504f28408510944876c706781e2469463b4f4716f20e5928ed9",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/QuanserHelicopter_results.json": "a747b56ce54b2cf4a403145a191f2e4edd66e51a5a078047d59622c6ef91e97e",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed123/TwoLinkManipulator_results.json": "cbafa68b3ae25cac7358ee7921c6cd97f880b8c079e6bdd0cb94968fe60f3ce1",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/AircraftPitch_results.json": "3164bb4cd4a8ab82c7d81077ae7d41a62a50876bfb5ad36dac7b35fc7f3db4a2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/AUV_results.json": "e1a450c268a6f137fdd7a566d2274c7de39fa1a56f52347e5c9e1b793df8c677",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/BallBeam_results.json": "22d8e46f63ed5bee87a2e07c2397416c807fd6b445de736e897b6b2621a1b24d",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/CartPole_results.json": "a47d8fbdfeb3deac74042b46beb017176ebd0272f7d9ffcc7cad29b5cb246bfc",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/CSTR_results.json": "31b9c9b357e6a4fd963deed303a3dc0cd4efc10293f43f4c783344849ec5989e",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/DCMotor_results.json": "61d1fbeba91c11ebb2d95983d360823354d86a22a5eadd4053daca2b90779951",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/InvPendulum_results.json": "d8592f22dc1aa5fc9d319958015b807e4afe688e5f78159ecb22255198c79b55",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/QuanserHelicopter_results.json": "9e29e8aae319dd7242ad998c64e67c24463430a773cf18ea99d8ca7dba28b7cc",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/gpt-4.1-nano/seed2024/TwoLinkManipulator_results.json": "a0fb1ac2744a20895e996a8a5eb8c962cfdba5f6dc20cd37e16d0930811f8fd8",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/AircraftPitch_results.json": "497724654b2fbc91451a25d0a193c4aa9f59823a6805bf1c957c160607d6bd35",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/AUV_results.json": "affe9a9b32fdf1c6fc0cb40a520e14263efa7a464b7e6741e2e151a883244fec",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/BallBeam_results.json": "569e71c5b185700a2bd6d2cf726d99372d34c203b137f1e2be0dec4b1abc17d5",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/CartPole_results.json": "189b35aa1f04537baa4923ca950dcb426abb824b7a3f4f4efe13e84e84152e1b",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/CSTR_results.json": "9dde301148606539cdbf3a78bc2aaa39c941dd0f58ef933c695d527754a748a2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/DCMotor_results.json": "06dd9baea08585775a5f2d41dbd0870f06d9667c901a997112ca9d7b8febbd95",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/InvPendulum_results.json": "a2b38e0142b673b3f90ad7dd01d1834b45e05d86776ca18b9d61f7ac3459d744",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/QuanserHelicopter_results.json": "43cc8a762f4bd804af3abecebde6172bfce86e678bae6e7130c5c1c596787aa2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed42/TwoLinkManipulator_results.json": "aad19808820f40b06b9aa4f1c40378e29ebb1b2002229192673dc3eb9209c4d2",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/AircraftPitch_results.json": "cee7c413e1b12b0b9a8d0047d4da82f473d3ca8436ce491647e24d8171f521c4",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/AUV_results.json": "a6f264ea387a4860e8b24f11273718dc1fe49e9f47f4de67c92f9a4875d382af",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/BallBeam_results.json": "5d7771607096a349a18a6f5471c83563a84fc58a44bf1510e2db8a8e2cc2e031",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/CartPole_results.json": "b448c6f74dc68d1ddd928afd0519e2fde8dee42362cec205986f107a6390efe4",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/CSTR_results.json": "7ea6f57342cada16815ffb46b256c1e56eb4b86e746be3143d4633fa56061332",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/DCMotor_results.json": "430028d00684528426e0778a4765958170473c3368bb505dadf5211365b207a9",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/InvPendulum_results.json": "ba679f46bc2d0999518cc7df03b25fdb4a0cff474f2535af3a185f43d631ce00",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/QuanserHelicopter_results.json": "4a883456a2b4b1e2ddfbf7a77e5900d5662b37773a25d4c61609d04218d04836",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed123/TwoLinkManipulator_results.json": "158fa64e7003a585712aed648e792274508d93e4b4f1c0433c2fd8f4d330469a",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/AircraftPitch_results.json": "14061fc2a18406bffee02300c307e2969829bb475d6552ee508a19c14d940ccd",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/AUV_results.json": "b3839e6e38df95ec841cba594cbd692b040bce007823233bee8633f054f5fb98",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/BallBeam_results.json": "f7dca7b35861487f0a5183ed86060e9841c87c76d60c63805f770cfcc72e5709",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/CartPole_results.json": "d1535b1fec090d8fd5eea0a2e0c1679814a985f4740c68738a70e51e2888dc82",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/CSTR_results.json": "c9edf254cb0f7257bf43271fbed30bf0bc8e029dd450281f3dba9686e9bb5979",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/DCMotor_results.json": "2025da98d74af13b7604aa024f516ef814a4ad47c9003d7512d8f37b886a0669",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/InvPendulum_results.json": "6045f554a8c99a7ec3bd998569f8f5f6f22850854dbb225ca31ea09c91aa8a00",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/QuanserHelicopter_results.json": "ccd594b16b3ff5837f8b94e139a0f393f584435f30d1c2f0e1d85c6aaba8f4a4",
        "benchmarks/MPC/json_reports/results/2026-10-18_12h/groq-gpt-oss-120b/seed2024/TwoLinkManipulator_results.json": "4a93f7b8ba0acc25d01eb09349277ceb667a6d19a50c343ee82794bbbf7264ea"
      }
    },
    "Adaptive": {
      "batch": "2026-10-17_17h",
      "timestamp_meaning": "Archive organization time, not original run date.",
      "records": 105,
      "cases": [
        "AUV.json",
        "BallBeam.json",
        "CartPole.json",
        "DCMotor.json",
        "InvPendulum.json",
        "QuanserHelicopter.json",
        "TwoLinkManipulator.json"
      ],
      "n_seeds_per_case_model": 3,
      "cost_and_success": [
        {
          "model": "gpt-5.4-mini",
          "n": 21,
          "success": 0.8599052857142857,
          "cost": 0.013120821428571426
        },
        {
          "model": "gpt-5.4-nano",
          "n": 21,
          "success": 0.8628574285714286,
          "cost": 0.0034482690476190475
        },
        {
          "model": "gpt-4o-mini",
          "n": 21,
          "success": 0.8827784285714285,
          "cost": 0.0021550499999999995
        },
        {
          "model": "gpt-4.1-nano",
          "n": 21,
          "success": 0.8858994761904763,
          "cost": 0.001754695238095238
        },
        {
          "model": "groq-gpt-oss-120b",
          "n": 21,
          "success": 0.8700973333333334,
          "cost": 0.006530865238095237
        }
      ],
      "source_bar_figure": "benchmarks/Adaptive/plots/2026-10-17_17h/dashboard/seed_statistics/success_rate_6_seed_statistics.png",
      "source_bar_sha256": "2d4a7793493e91973b27f134c682e07b7d0eabb6da4d5a09ceb00753eb2fca88",
      "copied_bar_sha256": "2d4a7793493e91973b27f134c682e07b7d0eabb6da4d5a09ceb00753eb2fca88",
      "example": {
        "json": "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/AUV_results.json",
        "json_sha256": "accbd1d1315f67b9fd3fc749dff36f650c6b529b3ad77d6c79e8db480efc4263",
        "trajectory": "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/trajectories/AUV_test_1_verification.npz",
        "trajectory_sha256": "5f2dfcf332d54e4d4ab0ad8be035d87fee0ee07a622107c428b7046bfbf6b32b",
        "samples": 2000,
        "recorded_duration_s": 19.990000000000325,
        "success_rate_6": 0.923905,
        "category_checks": {
          "mse_max": {
            "limit": [
              0.05
            ],
            "measured_value": [
              0.03626421546510514
            ],
            "comparison": "<=",
            "passed": true,
            "source": "verification.tracking_mse.full (each named controlled output)",
            "score": 0.9398557207005479,
            "outputs": [
              "depth"
            ],
            "per_output": {
              "depth": {
                "limit": 0.05,
                "measured_value": 0.03626421546510514,
                "passed": true,
                "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance.",
                "score": 0.9398557207005479
              }
            },
            "unavailable_outputs": [],
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "settling_time_max_s": {
            "limit": 4.0,
            "measured_value": 2.99999999999998,
            "comparison": "<=",
            "passed": true,
            "source": "verification.settling_time, with settling_time_reached=true",
            "settled": true,
            "score": 0.9284249141675281,
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "overshoot_max_pct": {
            "limit": [
              5.0
            ],
            "measured_value": [
              0.0
            ],
            "comparison": "<=",
            "passed": true,
            "source": "series.trajectory_file: trajectories/AUV_test_1_verification.npz (outputs, reference, times)",
            "score": 1.0,
            "outputs": [
              "depth"
            ],
            "per_output": {
              "depth": {
                "limit": 5.0,
                "measured_value": 0.0,
                "passed": true,
                "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance.",
                "exact": true,
                "score": 1.0
              }
            },
            "unavailable_outputs": [],
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          },
          "control_effort_max": {
            "limit": 0.0125,
            "measured_value": 0.012285323113292139,
            "comparison": "<=",
            "passed": true,
            "source": "mean_j(verification.control_rms[j] ** 2)",
            "score": 0.8273404157602385,
            "reason": "For a positive limit, full credit up to the configured fraction of the limit; exponential credit above that allowance."
          }
        }
      },
      "score_parameters": {
        "half_credit_ratio": 2.0,
        "zero_limit_tolerances": {},
        "full_credit_fraction": 0.6
      },
      "source_reports_unchanged": true,
      "cases_by_model": {
        "AUV.json": {
          "gpt-5.4-mini": 0.9066783333333334,
          "gpt-5.4-nano": 0.890419,
          "gpt-4o-mini": 0.933698,
          "gpt-4.1-nano": 0.9197483333333333,
          "groq-gpt-oss-120b": 0.8699183333333332
        },
        "BallBeam.json": {
          "gpt-5.4-mini": 0.739847,
          "gpt-5.4-nano": 0.7584046666666667,
          "gpt-4o-mini": 0.763742,
          "gpt-4.1-nano": 0.751337,
          "groq-gpt-oss-120b": 0.751337
        },
        "CartPole.json": {
          "gpt-5.4-mini": 0.9935136666666667,
          "gpt-5.4-nano": 0.9961666666666668,
          "gpt-4o-mini": 0.9906280000000001,
          "gpt-4.1-nano": 0.9991343333333335,
          "groq-gpt-oss-120b": 1.0
        },
        "DCMotor.json": {
          "gpt-5.4-mini": 0.658158,
          "gpt-5.4-nano": 0.658158,
          "gpt-4o-mini": 0.7799153333333333,
          "gpt-4.1-nano": 0.8086496666666666,
          "groq-gpt-oss-120b": 0.658158
        },
        "InvPendulum.json": {
          "gpt-5.4-mini": 0.9820653333333333,
          "gpt-5.4-nano": 0.9967183333333334,
          "gpt-4o-mini": 0.9870096666666667,
          "gpt-4.1-nano": 0.9946930000000002,
          "groq-gpt-oss-120b": 0.9957056666666668
        },
        "QuanserHelicopter.json": {
          "gpt-5.4-mini": 0.9686366666666667,
          "gpt-5.4-nano": 0.97004,
          "gpt-4o-mini": 0.954018,
          "gpt-4.1-nano": 0.957296,
          "groq-gpt-oss-120b": 1.0
        },
        "TwoLinkManipulator.json": {
          "gpt-5.4-mini": 0.770438,
          "gpt-5.4-nano": 0.7700953333333334,
          "gpt-4o-mini": 0.770438,
          "gpt-4.1-nano": 0.770438,
          "groq-gpt-oss-120b": 0.8155623333333333
        }
      },
      "report_sha256": {
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/AUV_results.json": "f9faa86bfacad5980eef91cb62ff48baec2173943ec7c272a96e2e2b579d537e",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/BallBeam_results.json": "476f4df91c7eb1fa3371cd5f365faa84d89ea9fe0268a51af718f58209c03685",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/CartPole_results.json": "ab2e3527849966af2f24983c258fc67d4d38909ba082ddd597558f831f93c66a",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/DCMotor_results.json": "d0d78f2ad9de33f0d068067304422ff4819fd10a51cda9427a47887103e963e7",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/InvPendulum_results.json": "57a6fe66d91efd80e89b856ac1053206e6be4b8c34286dce08eeaecf79592a11",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/QuanserHelicopter_results.json": "e8fcfb774f9964f4af06b9534491466b6016660d229f278ec57ea100c7be0367",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed42/TwoLinkManipulator_results.json": "78ec1757b702bcb0426fd515f4d52de04d46a3bd8d10ed5e629e9a7e1ad7723b",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/AUV_results.json": "8b16ddfee8b420f57b00f41fc9ab8eec8565c6c35da05efd1874837af6b4afbf",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/BallBeam_results.json": "c53822e0767093688fa6e177b3af189c736677a8ba540c773336f35073b00432",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/CartPole_results.json": "dd0d49a9f82f869894c6d7b52edc4dde75b7993aa54cddbabb65d41ecf2d682d",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/DCMotor_results.json": "310aac4f88086fba54cf10bfcb0fdc1e7252116cf74693db9e420efec351b446",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/InvPendulum_results.json": "293538d6db7425d3f92790008d1d937fcfd84b1dafa51dfc843187202eac19dd",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/QuanserHelicopter_results.json": "73211927c26e4f94cd0f7b37a11c00e771c4c9a526d11181bb5c2443954b75fc",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed123/TwoLinkManipulator_results.json": "5f7a66d57786e02a77b66921cd2229a5e48f15bc31e7ae70f729d45fbc1027e2",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/AUV_results.json": "069c407e7aa69bfabc733757bafb989c2cff9b7028c5fc6120b882abe0a8aca9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/BallBeam_results.json": "6b526966630dd3330f6455db5a9863ace2b6860397875c9cfc4883570c70fd12",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/CartPole_results.json": "cf93f0d5efd815c18476ff3efa42f61f86813a2695e6b7eabddd72cfcd065db0",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/DCMotor_results.json": "2152e5efbdccf23021a4114c1747757811e3ec120dee4a78e42fa064e08edda6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/InvPendulum_results.json": "40ecbbe67ad2883b698d3c8c38c9a4daa1f9485786329b11a026a6bf23cf2e11",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/QuanserHelicopter_results.json": "6506603fe83cee332eb08a4f235ecec17cadf93fdafaacb171aa628ee0d3142c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-mini/seed2024/TwoLinkManipulator_results.json": "b83861635871bd2330f81bf033edda777c04f568c14f0a8024b819791f4e064f",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/AUV_results.json": "71ecab335efa3b33ade4c54ab81dde67e7e70e5dd962dec5a4b55a1cf4b8c822",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/BallBeam_results.json": "77674968b4752d960854fe428832bbe701d1bee1125cf27aa8e53d60406d57d2",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/CartPole_results.json": "6ab4c76724fcf8929813db1bde517241955d5ee64a69662e32db6bd7d6e5a74c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/DCMotor_results.json": "d6ac142e2016904c2b68e3f1cfaa0894253c22fc08b71a942464b3cacf44d376",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/InvPendulum_results.json": "b957ab1e7a1c084730cea5e71a7e324bb2dd69b47bc3c2268bbb63bb5b7e66e6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/QuanserHelicopter_results.json": "8dfe1547e0c6cb5b27a027ba18d87d09f655a78ea27df69293719cc06077463b",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed42/TwoLinkManipulator_results.json": "9ffc72441a927db8b17fa0c3a2d4571dc96aba66231e623a5adbdc4ff8daa6bd",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/AUV_results.json": "7b8981ae86ad49da7806c51f32a6fe31d9e85810e0d9f72a4edb434bba47ab03",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/BallBeam_results.json": "2c6930d5e6b015f2c567bc9434ee417412487aedc7176fa6090d79666a66fde5",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/CartPole_results.json": "03398e2965d2af2467016d7160991084379e822e8309c8ef5cddb1d185538466",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/DCMotor_results.json": "04b05190297cd8b5094cd35a337a63e4200a16f545307ab709ac066aa35cd3f9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/InvPendulum_results.json": "c67fe4f405e3afd6b6c8d4b2cbad1a21967fdeb6a81065ca62a640e763b7ea23",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/QuanserHelicopter_results.json": "f80bbc405d55a162ce07d473fca3da4af4cf6ca083b9435e27f364371ea91ee3",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed123/TwoLinkManipulator_results.json": "989f3744db71f9b989cda08aa01445b83a1edcafa71ef246a7a0d49d88c3514a",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/AUV_results.json": "dd47e2ebf1f52a6d91fcfd621478f09165199cbff2de9b06b2ee1952727ca222",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/BallBeam_results.json": "63f4df010cce9c72ab4683b49aed2ca3f8c48b227be7ee815047372a5e2ff9e9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/CartPole_results.json": "c6216d02753cdbaa5712c74eec05124d0edfe62d5f11d189d2816372bad60800",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/DCMotor_results.json": "1b3fc7ebb6d8f51c0fd8a1b8ffe37033b5a6f119bb088773197180f6c42acc62",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/InvPendulum_results.json": "bc23eab37caf80d8d091f0a94c6dcb15670ac1d4a676bf07ecd01ca647b58933",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/QuanserHelicopter_results.json": "f40015ce357c5a54ac365c5f3e82a46089a828721a599b1081dd7d1071d06881",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-5.4-nano/seed2024/TwoLinkManipulator_results.json": "e17d4c38ae1674cfd961b705644f8030e634c643c24179c196b3168b5587d3c6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/AUV_results.json": "7d3f9ea671496d3fbf4bb35c2533c861b72af266cf144caf658000026a09809b",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/BallBeam_results.json": "a4e13326915a7ed4723897a4b2366f773c811628bec41f620a05f8bf706ea9b7",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/CartPole_results.json": "48610e5100474eed624dbbacef08af89939b42b91359debc37e3278ae54d49b6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/DCMotor_results.json": "e3490df4f317e0ee8ed79baa116e48c96c45df3b7b3dd1387f26f77a2cb683e3",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/InvPendulum_results.json": "bef2848e1cfa147db75d23a4a7dc9229c87783353ab25ce737271b817f4c761e",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/QuanserHelicopter_results.json": "efb473ac36f94de44ebcef3fdcd1201d33f6ebef2a2c84c31439fb8f491a8be0",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed42/TwoLinkManipulator_results.json": "254dc936e72a07a18b691c3c46edf1df6bf041bcb1ddea652e1bdff8b5f48359",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/AUV_results.json": "7aa7efa92cbd2c83b88d89fc7705448836acdf9fd7bcacffad5332b99668fe88",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/BallBeam_results.json": "480c26752c9ee4ff0869e5ad807240449d7511b397c32956111ff4bfdd58ccf4",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/CartPole_results.json": "2c0a3a776d3a7bb5f726462ec7c73870787a3a9278fe050b79ba7a9a2293d4c8",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/DCMotor_results.json": "ce0b0a3e9de1fcd5cf021a5731f2bb7debfb8c93ef62142c19316de8e8691f1c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/InvPendulum_results.json": "9fc71316fb64e084ecb309ea304e68eeaeab7cda83aa49047cc8ea482c5bd61e",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/QuanserHelicopter_results.json": "1658759966b3453278bf80842245245630bb16e533be7b544c12b972f4d6589b",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed123/TwoLinkManipulator_results.json": "424837ee22015a34c57e5146a2ee93a5d3fbc5cc3affc76894125190f9967182",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/AUV_results.json": "21b20b976a11e5f40e62a16ef109c4ac8fd9eba93d142a5844c419c5b9550594",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/BallBeam_results.json": "10610e4c2cb56d39ebb0a850df4b1643be05d5f3dce3e0195854c29980ac20a9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/CartPole_results.json": "e2b00a161e9c75e9e406ad567620f55da366fb61a0ad7de76aef847299ca367d",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/DCMotor_results.json": "4dd9bc028326545bd94e267ba99575f9abddbe172f666e0147c677c391718e56",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/InvPendulum_results.json": "6b7b9258cac18874498dd069bb2278edf7948bd4c570ac89f361059e89cb1264",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/QuanserHelicopter_results.json": "dfbe4bcebda145105684ac714951ed054a662eb5b8ebd65e4859f88f36c872ce",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4o-mini/seed2024/TwoLinkManipulator_results.json": "e7252e7ffba97edf33a0f2b673ca45bc5dbbd7f3c82ac3ba7a9ab5e50725353b",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/AUV_results.json": "accbd1d1315f67b9fd3fc749dff36f650c6b529b3ad77d6c79e8db480efc4263",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/BallBeam_results.json": "e8e3e27797f628b36528379cd0b6515aa54bbafd303f1bae56c3a524e22fef16",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/CartPole_results.json": "0ee6ee8fe247ce8f70fa1e951f00746e952d019c642ad03887afe5f5e2745e32",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/DCMotor_results.json": "ae9d3298a808b9c97361604366e103cf7027dc07540d45c8ddf96c5968efb157",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/InvPendulum_results.json": "193e5c419be803c46aa870fa802efe52beb34fea7ff68c25cd7d9426effbd111",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/QuanserHelicopter_results.json": "a6497c58e598fa4e4a481dbd556159c0306804f8c4a327a734790680691090b6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed42/TwoLinkManipulator_results.json": "2ab6c9fd3a9bd3f11ef88d7a32589adf58612b534e18b21e369ccb1ec0b4ce50",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/AUV_results.json": "2cc22645549e3cd212fe90256b27e50bf89a47ce4e72ccca17018e91f585839a",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/BallBeam_results.json": "7eefaf127ef767dda50eca5be7dc6345e01c05319511adb66e35ed62cca2eb57",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/CartPole_results.json": "d1244a27c462a495cb6a1a42927a066f7c9a41693020f7980402d74fa8bd99af",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/DCMotor_results.json": "cda49a90f9fe7027a38a130f1aed737f62294d373c1dd10c00b2f37b5c8e728d",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/InvPendulum_results.json": "f653db0c95d5fd8b1add85efae7381ce5f7f4c082ffe21e25fd71821d7787fa0",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/QuanserHelicopter_results.json": "ddef75c9b332f55b0e60f15e0bc59a07dff96df4c528c9cf4983f4b903d7e0a9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed123/TwoLinkManipulator_results.json": "769efa2befddfeb4e3d5fa3e6f3778bee9c9c6b08b728359792622ec03871b21",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/AUV_results.json": "e61b1d66461208285e4bf2503ea0c82bb888d5adacdf0ccc56b45e4f4940ae37",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/BallBeam_results.json": "16d47da7f16b9d6655b5998e6e4f394765a908eb11bcea2b24c91c5c776079e1",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/CartPole_results.json": "3d48e519cee16a64a36f0493b9bdb76ae8ec2fde40b4c27448d8e17f139de35c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/DCMotor_results.json": "1718b5a315e5ea84561ef6ec7f8bf72281ac9a533f0f756304ae595632e96c8c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/InvPendulum_results.json": "7f5cf2c5d9a2b1a89de2bf4c4e531a3f4856ce69a851dc5ba0e5693c7130f98a",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/QuanserHelicopter_results.json": "49716b143b065a79a077e664c0fd0b00dec1faf0d7352dad54ef602e9fc5fb6c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/gpt-4.1-nano/seed2024/TwoLinkManipulator_results.json": "a5411a2b4ebe9a027f29a498c1f904cc14c23a549c53aa64d66781d9b6521c85",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/AUV_results.json": "f3822f641823e64aed223cffbc808055006d8f8d3c03ce1b6656fc2dd4b87474",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/BallBeam_results.json": "ff92e97abec0c60cc6e0034467678f4ff13b5217a80212f67a063d6aeaaf9309",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/CartPole_results.json": "98aca56ba52b6c3b5c677c9f9edacd260270cb1350b39001f6a149d8cd1916a5",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/DCMotor_results.json": "bbd2f54a258eaf38ff148ea6544bdf9f8e694a5043484a685e0193bede8ea1f7",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/InvPendulum_results.json": "37d7db806269da21b22aa13f4d4e76ef90092b42cefd14e749ce878fc65e59c6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/QuanserHelicopter_results.json": "6abdd4bd1a1784897fec110ba125c7e3d98181302e1bbf850e2e2e0b171224b6",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed42/TwoLinkManipulator_results.json": "ed8f390ea0aeaa8a23e1fab69293ea81fe36edbe3e088e2f65fb06171f8b4166",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/AUV_results.json": "8b9203bcbb99b248da6e785e701d14fabff51098baa0672fb8c7268a66e96041",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/BallBeam_results.json": "bcf8d98d421c9d8246627e45b53602122fcefb27b024d64dc046d006cc4829f9",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/CartPole_results.json": "b59b48db05de83a628ebc0e87dd7e626e70c5d8e8ad1db05bbf6bf959090a881",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/DCMotor_results.json": "3963974c6ec78e17e42797585518e5425c273e2fa078b58d592efc71375a2671",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/InvPendulum_results.json": "539adf11f71392fae74b0dc1f229728bcd1b934c10d6d81bad1c3fd3a6a6b4f8",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/QuanserHelicopter_results.json": "307793ad0a79fbeb6ef23afa3b6d285050c921d6b9c52f431ffed64a0f548a71",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed123/TwoLinkManipulator_results.json": "c7044d3921d2f69d92ec29ffbadd28a54ef60f5d5d3e9950745d9dbda6b949fc",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/AUV_results.json": "8ec4f352b2de76d17f7d79d7b6220adf0acb7d205e719a0a91b42379607c62fc",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/BallBeam_results.json": "d7e274a1b964e413cb94aefce0a1c43055cf266da9adc31f1fa18b05c4277a6f",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/CartPole_results.json": "ef240ce9ba5405adaafe4f0ccefdeab3dc6458e2e36f6faf8efc1a089fbf090c",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/DCMotor_results.json": "040086d7d4ffe0f8304b5b76c02da0d642666d6d04ca87402190750ae3860da8",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/InvPendulum_results.json": "5cb5378ad68dae53614a997e6693a726a261f83dce3b279903d76aa1c02e2921",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/QuanserHelicopter_results.json": "c1e2255bbb82c877196c5aa6eae3895be1bd4d9f4fa92d3df2d59e675e9cf61f",
        "benchmarks/Adaptive/json_reports/results/2026-10-17_17h/groq-gpt-oss-120b/seed2024/TwoLinkManipulator_results.json": "94bb3178523db34493b788280970d070d07f3adbdfc3e3b3369621f18ef096c2"
      }
    }
  }
}
