{
  "protocol": "v3.0.1",
  "tier": "Quick Screen",
  "status": "complete",
  "completed_at": "2026-10-19T23:21:40.306620+00:00",
  "profiles": [
    {
      "id": "qwen36-ud-q3_k_m-reserve1024",
      "label": "Qwen3.6 35B-A3B",
      "quant": "UD-Q3_K_M",
      "status": "completed",
      "wall_s": 859.6446774239885,
      "model_source": {
        "repository": "unsloth/Qwen3.6-35B-A3B-MTP-GGUF",
        "revision": "5bc3e238d916f48a861bac2f8a1990a0e9b7e98d",
        "files": [
          {
            "filename": "Qwen3.6-35B-A3B-UD-Q3_K_M.gguf",
            "bytes": 17104402720,
            "sha256": "8966dd0cd8c543c4228490a2a8b0e0814fc4f1e6a8e199ceed4de6754ae7b8e1"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "tail-skip": "6",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {}
      },
      "initial_expert_profile_sha256": "b28390c7f0eb6ed55b7bcaec5644640135de0becaa9a093580f9c80ffb00605c",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 0,
      "business_scheduled": 6,
      "business_wilson95": [
        2.7755575615628914e-17,
        0.3903342879021653
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.18333333333333335,
      "coding_passes": 1,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.04558726080970055,
        0.6993581574175981
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": false,
      "transport_errors": 1,
      "gpu_fault_detected": false,
      "context_window_rejections": [
        {
          "prompt_tokens": 67404,
          "requested_output_tokens": 2048,
          "configured_context": 65536
        }
      ],
      "startup_wall_s": 5.231171149993315,
      "resources": {
        "samples": 177,
        "observed_peak_vram_bytes": 11806748672,
        "guest_peak_cgroup_memory_bytes": 28741287936,
        "observed_min_free_vram_bytes": 1061376000,
        "maximum_available_gpu_sensor_c": 88.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 12.247045055992203,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 5366,
          "recorded_completion_tokens": 702,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 24.798166867985856,
          "tool_calls": 3,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 4,
          "recorded_prompt_tokens": 9480,
          "recorded_completion_tokens": 1647,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.5,
          "terminal": "final_answer",
          "wall_s": 41.460253130004276,
          "tool_calls": 11,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 9,
          "recorded_prompt_tokens": 52958,
          "recorded_completion_tokens": 2182,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.6,
          "terminal": "final_answer",
          "wall_s": 86.02922583400505,
          "tool_calls": 25,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 60092,
          "recorded_completion_tokens": 5969,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "transport_or_protocol_error",
          "wall_s": 179.6613877680211,
          "tool_calls": 68,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": 400,
          "model_calls": 14,
          "recorded_prompt_tokens": 388355,
          "recorded_completion_tokens": 3934,
          "empty_responses": 0
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 171.97834667400457,
          "tool_calls": 39,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 245379,
          "recorded_completion_tokens": 9436,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 67.5963177959784,
          "tool_calls": 9,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 2,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 5,
          "recorded_prompt_tokens": 23687,
          "recorded_completion_tokens": 4996,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 82.6542745839979,
          "tool_calls": 31,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 6,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains",
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 204439,
          "recorded_completion_tokens": 3153,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 8.534049627021886,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 36.66995085100643,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 43,
          "wall_s": 53.69622417501523,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 42,
          "wall_s": 53.85069473698968,
          "finish_reason": "length"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 3.807566609000787,
          "ttft_s": 0.3754061259969603,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 67.23454276409406
        },
        {
          "kind": "generation-1",
          "wall_s": 3.4989627889881376,
          "ttft_s": 0.12343358300859109,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 73.1645391616275
        },
        {
          "kind": "generation-2",
          "wall_s": 3.4051109820138663,
          "ttft_s": 0.022403845010558143,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 75.18110315705343
        },
        {
          "kind": "prefill-0",
          "wall_s": 5.554195220000111,
          "ttft_s": 1.905042466998566,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 46.091285930708594
        },
        {
          "kind": "prefill-1",
          "wall_s": 3.342167162016267,
          "ttft_s": 0.02336485401610844,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 76.59700654995365
        },
        {
          "kind": "prefill-2",
          "wall_s": 3.5333872310002334,
          "ttft_s": 0.023457123985281214,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 72.45172500596017
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.12343358300859109,
        "first_request_ttft_s": 0.3754061259969603,
        "cached_prompt_tokens": [
          0,
          28,
          28
        ],
        "median_wall_s": 3.4989627889881376,
        "median_completion_tokens_per_end_to_end_s": 73.1645391616275,
        "actual_prompt_tokens": [
          29,
          29,
          29
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.023457123985281214,
        "first_request_ttft_s": 1.905042466998566,
        "cached_prompt_tokens": [
          0,
          1521,
          1521
        ],
        "median_wall_s": 3.5333872310002334,
        "median_completion_tokens_per_end_to_end_s": 72.45172500596017,
        "actual_prompt_tokens": [
          1522,
          1522,
          1522
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": false
    },
    {
      "id": "ornith-apex-i-compact-reserve1024",
      "label": "Ornith 1.5",
      "quant": "APEX-I-COMPACT",
      "status": "completed",
      "wall_s": 1003.7423945330083,
      "model_source": {
        "repository": "mudler/Ornith-1.5-35B-A3B-APEX-MTP-GGUF",
        "revision": "4c326713c52d13fdb40983a2a09a46cca8e88739",
        "files": [
          {
            "filename": "Ornith-1.5-35B-A3B-APEX-MTP-I-Compact.gguf",
            "bytes": 17437861408,
            "sha256": "67e6cdff678e67180d3cd4eef55277277563319057de287b8855c4d1fbff4165"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {}
      },
      "initial_expert_profile_sha256": "beef3742fb8a6ec44486c362a5a19442f89ab3cb7e33c48003cfe67e75b952a7",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 0,
      "business_scheduled": 6,
      "business_wilson95": [
        2.7755575615628914e-17,
        0.3903342879021653
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.03333333333333333,
      "coding_passes": 1,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.04558726080970055,
        0.6993581574175981
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": true,
      "transport_errors": 0,
      "gpu_fault_detected": false,
      "context_window_rejections": [],
      "startup_wall_s": 30.83101767700282,
      "resources": {
        "samples": 201,
        "observed_peak_vram_bytes": 11804540928,
        "guest_peak_cgroup_memory_bytes": 29851185152,
        "observed_min_free_vram_bytes": 1063583744,
        "maximum_available_gpu_sensor_c": 88.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 10.866856108012144,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 5385,
          "recorded_completion_tokens": 287,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 23.57111965000513,
          "tool_calls": 4,
          "tool_execution_errors": 1,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 4,
          "recorded_prompt_tokens": 12371,
          "recorded_completion_tokens": 1143,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 117.49086434202036,
          "tool_calls": 42,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 3,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 181553,
          "recorded_completion_tokens": 5245,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.2,
          "terminal": "final_answer",
          "wall_s": 100.08182202198077,
          "tool_calls": 16,
          "tool_execution_errors": 1,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 7,
          "recorded_prompt_tokens": 50563,
          "recorded_completion_tokens": 5646,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "timeout",
          "wall_s": 180.00290327999392,
          "tool_calls": 51,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 7,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": null,
          "model_calls": 15,
          "recorded_prompt_tokens": 330868,
          "recorded_completion_tokens": 5649,
          "empty_responses": 0
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 147.90332250099164,
          "tool_calls": 48,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 13,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 357229,
          "recorded_completion_tokens": 3604,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 125.58898984399275,
          "tool_calls": 28,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 3,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 158797,
          "recorded_completion_tokens": 6487,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 99.98584484800813,
          "tool_calls": 30,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 7,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains",
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 184897,
          "recorded_completion_tokens": 4525,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 3.3095492780266795,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 27.396677878015907,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 65.97938666501432,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 42,
          "wall_s": 31.677351610996993,
          "finish_reason": "stop"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 4.63346559900674,
          "ttft_s": 0.3860234320163727,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 55.25022135804306
        },
        {
          "kind": "generation-1",
          "wall_s": 4.022473054006696,
          "ttft_s": 0.021393261005869135,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 63.64244000217829
        },
        {
          "kind": "generation-2",
          "wall_s": 3.919705502979923,
          "ttft_s": 0.020766289992025122,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 65.31102905699883
        },
        {
          "kind": "prefill-0",
          "wall_s": 5.898341787979007,
          "ttft_s": 1.8909998719755094,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 43.4020287738726
        },
        {
          "kind": "prefill-1",
          "wall_s": 4.083402754011331,
          "ttft_s": 0.021913431002758443,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 62.69281171163397
        },
        {
          "kind": "prefill-2",
          "wall_s": 3.944646645017201,
          "ttft_s": 0.022069441009080037,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 64.89808163764785
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.021393261005869135,
        "first_request_ttft_s": 0.3860234320163727,
        "cached_prompt_tokens": [
          0,
          28,
          28
        ],
        "median_wall_s": 4.022473054006696,
        "median_completion_tokens_per_end_to_end_s": 63.64244000217829,
        "actual_prompt_tokens": [
          29,
          29,
          29
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.022069441009080037,
        "first_request_ttft_s": 1.8909998719755094,
        "cached_prompt_tokens": [
          0,
          1521,
          1521
        ],
        "median_wall_s": 4.083402754011331,
        "median_completion_tokens_per_end_to_end_s": 62.69281171163397,
        "actual_prompt_tokens": [
          1522,
          1522,
          1522
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": false
    },
    {
      "id": "tiel-ud-q3_k_xl-reserve1024",
      "label": "Tiel Coder 35B-A3B",
      "quant": "UD-Q3_K_XL",
      "status": "completed",
      "wall_s": 976.0521235009946,
      "model_source": {
        "repository": "peculiar-ragdoll/Tiel-Coder-35B-A3B-GGUF-MTP",
        "revision": "bbe9e566f39e4fc9652ac66b71968289a03c520a",
        "files": [
          {
            "filename": "Tiel-Coder-35B-A3B-MTP-UD-Q3_K_XL.gguf",
            "bytes": 17234935648,
            "sha256": "46b8fbeba6e888c9a101e49cc717baa9bb8dfa0d203ec7b3185288159543ec14"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {}
      },
      "initial_expert_profile_sha256": "3e4decf5774a6006cb983886a7dc6e5ef3c85fbfd996f8d2000a0885b53e3cfc",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 0,
      "business_scheduled": 6,
      "business_wilson95": [
        2.7755575615628914e-17,
        0.3903342879021653
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.18125,
      "coding_passes": 2,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.15003898915214947,
        0.8499610108478506
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": true,
      "transport_errors": 0,
      "gpu_fault_detected": false,
      "context_window_rejections": [],
      "startup_wall_s": 25.77987452200614,
      "resources": {
        "samples": 195,
        "observed_peak_vram_bytes": 11807240192,
        "guest_peak_cgroup_memory_bytes": 29911560192,
        "observed_min_free_vram_bytes": 1060884480,
        "maximum_available_gpu_sensor_c": 88.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 12.801966687984532,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 6224,
          "recorded_completion_tokens": 271,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 35.547075888986,
          "tool_calls": 5,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 6,
          "recorded_prompt_tokens": 19212,
          "recorded_completion_tokens": 1902,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.5,
          "terminal": "final_answer",
          "wall_s": 53.00930534800864,
          "tool_calls": 13,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 55658,
          "recorded_completion_tokens": 2581,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.1875,
          "terminal": "timeout",
          "wall_s": 180.0023183330195,
          "tool_calls": 52,
          "tool_execution_errors": 1,
          "grading_error": false,
          "tool_returned_errors": 9,
          "failed_assertion_types": [
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains",
            "hubspot_contact_not_exists"
          ],
          "http_error_status": null,
          "model_calls": 15,
          "recorded_prompt_tokens": 193664,
          "recorded_completion_tokens": 8500,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 174.22351086401613,
          "tool_calls": 47,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 10,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 388156,
          "recorded_completion_tokens": 5718,
          "empty_responses": 0
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 85.34323112599668,
          "tool_calls": 44,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 7,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 12,
          "recorded_prompt_tokens": 140947,
          "recorded_completion_tokens": 3149,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 143.08525868100696,
          "tool_calls": 45,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 2,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 310267,
          "recorded_completion_tokens": 5130,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.4,
          "terminal": "final_answer",
          "wall_s": 134.00474137399578,
          "tool_calls": 20,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 3,
          "failed_assertion_types": [
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 15,
          "recorded_prompt_tokens": 143377,
          "recorded_completion_tokens": 8020,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 2.484956042986596,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 59.89668236300349,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 18.28707649098942,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 42,
          "wall_s": 20.58339428700856,
          "finish_reason": "stop"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 5.0326497010246385,
          "ttft_s": 0.8254548280092422,
          "usage": {
            "prompt_tokens": 207,
            "completion_tokens": 256,
            "total_tokens": 463,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 50.86783607209515
        },
        {
          "kind": "generation-1",
          "wall_s": 3.7914050010149367,
          "ttft_s": 0.02282077501877211,
          "usage": {
            "prompt_tokens": 207,
            "completion_tokens": 256,
            "total_tokens": 463,
            "prompt_tokens_details": {
              "cached_tokens": 206
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 67.52114319928108
        },
        {
          "kind": "generation-2",
          "wall_s": 3.7151014319970272,
          "ttft_s": 0.022370093007339165,
          "usage": {
            "prompt_tokens": 207,
            "completion_tokens": 256,
            "total_tokens": 463,
            "prompt_tokens_details": {
              "cached_tokens": 206
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 68.90794361498467
        },
        {
          "kind": "prefill-0",
          "wall_s": 4.003926503995899,
          "ttft_s": 1.9627315330144484,
          "usage": {
            "prompt_tokens": 1700,
            "completion_tokens": 139,
            "total_tokens": 1839,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 34.715921948437035
        },
        {
          "kind": "prefill-1",
          "wall_s": 0.6149554350122344,
          "ttft_s": 0.023381097009405494,
          "usage": {
            "prompt_tokens": 1700,
            "completion_tokens": 42,
            "total_tokens": 1742,
            "prompt_tokens_details": {
              "cached_tokens": 1699
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 68.29763200509711
        },
        {
          "kind": "prefill-2",
          "wall_s": 0.7219265240128152,
          "ttft_s": 0.023155816015787423,
          "usage": {
            "prompt_tokens": 1700,
            "completion_tokens": 50,
            "total_tokens": 1750,
            "prompt_tokens_details": {
              "cached_tokens": 1699
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 69.25912587624005
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.02282077501877211,
        "first_request_ttft_s": 0.8254548280092422,
        "cached_prompt_tokens": [
          0,
          206,
          206
        ],
        "median_wall_s": 3.7914050010149367,
        "median_completion_tokens_per_end_to_end_s": 67.52114319928108,
        "actual_prompt_tokens": [
          207,
          207,
          207
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.023381097009405494,
        "first_request_ttft_s": 1.9627315330144484,
        "cached_prompt_tokens": [
          0,
          1699,
          1699
        ],
        "median_wall_s": 0.7219265240128152,
        "median_completion_tokens_per_end_to_end_s": 68.29763200509711,
        "actual_prompt_tokens": [
          1700,
          1700,
          1700
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": true
    },
    {
      "id": "gemma4-ud-q4_k_m-reserve1024-thinkingoff",
      "label": "Gemma4 26B-A4B \u00b7 thinking off",
      "quant": "UD-Q4_K_M",
      "status": "completed",
      "wall_s": 393.0170254650002,
      "model_source": {
        "repository": "unsloth/gemma-4-26B-A4B-it-GGUF",
        "revision": "c099eb48e663fd284577b04978a94ffccb261841",
        "files": [
          {
            "filename": "gemma-4-26B-A4B-it-UD-Q4_K_M.gguf",
            "bytes": 16947541728,
            "sha256": "f2c28b3dc4776931ac6f879e11f203dec637ea0f14267a86ec8f6165f63f293f"
          },
          {
            "filename": "mtp-gemma-4-26B-A4B-it-Q8_0.gguf",
            "bytes": 461766816,
            "sha256": "6326fb9f5e487aa8dcdd313a091e3c67724cb2a666ec3b7d2895b5b26d93ed1b"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {
          "reasoning_effort": "none",
          "chat_template_kwargs": {
            "enable_thinking": false
          }
        }
      },
      "initial_expert_profile_sha256": "85bbbf6fd0b3ce46bb43cddb804733f90aa662cd3e174e624779a3511ddbad4b",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 0,
      "business_scheduled": 6,
      "business_wilson95": [
        2.7755575615628914e-17,
        0.3903342879021653
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.08333333333333333,
      "coding_passes": 2,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.15003898915214947,
        0.8499610108478506
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": true,
      "transport_errors": 0,
      "gpu_fault_detected": false,
      "context_window_rejections": [],
      "startup_wall_s": 20.574889929004712,
      "resources": {
        "samples": 79,
        "observed_peak_vram_bytes": 11826479104,
        "guest_peak_cgroup_memory_bytes": 29592584192,
        "observed_min_free_vram_bytes": 1041645568,
        "maximum_available_gpu_sensor_c": 86.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 9.651805400004378,
          "tool_calls": 3,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 4,
          "recorded_prompt_tokens": 6129,
          "recorded_completion_tokens": 185,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 40.535325017001014,
          "tool_calls": 15,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 75757,
          "recorded_completion_tokens": 2590,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.5,
          "terminal": "step_limit",
          "wall_s": 25.264881252020132,
          "tool_calls": 16,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 85767,
          "recorded_completion_tokens": 624,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 29.992974218999734,
          "tool_calls": 20,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains",
            "hubspot_contact_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 137696,
          "recorded_completion_tokens": 949,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "empty_final",
          "wall_s": 24.92616145100328,
          "tool_calls": 17,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 73554,
          "recorded_completion_tokens": 416,
          "empty_responses": 1
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 25.86238181599765,
          "tool_calls": 19,
          "tool_execution_errors": 3,
          "grading_error": false,
          "tool_returned_errors": 5,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 90887,
          "recorded_completion_tokens": 706,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 30.412006997008575,
          "tool_calls": 16,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 92619,
          "recorded_completion_tokens": 1110,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 29.467795116011985,
          "tool_calls": 16,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains",
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 124570,
          "recorded_completion_tokens": 365,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 3.2659786459989846,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 15.230187848996138,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 43,
          "wall_s": 50.92265928100096,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 42,
          "wall_s": 50.996932410023874,
          "finish_reason": "length"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 4.069651263998821,
          "ttft_s": 0.5000449980143458,
          "usage": {
            "prompt_tokens": 30,
            "completion_tokens": 256,
            "total_tokens": 286,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 62.90465285432234
        },
        {
          "kind": "generation-1",
          "wall_s": 3.3077639779949095,
          "ttft_s": 0.023184175981441513,
          "usage": {
            "prompt_tokens": 30,
            "completion_tokens": 256,
            "total_tokens": 286,
            "prompt_tokens_details": {
              "cached_tokens": 29
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 77.39367188924444
        },
        {
          "kind": "generation-2",
          "wall_s": 3.2023275950050447,
          "ttft_s": 0.022952564992010593,
          "usage": {
            "prompt_tokens": 30,
            "completion_tokens": 256,
            "total_tokens": 286,
            "prompt_tokens_details": {
              "cached_tokens": 29
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 79.94185241987921
        },
        {
          "kind": "prefill-0",
          "wall_s": 6.055637903016759,
          "ttft_s": 2.4318677200062666,
          "usage": {
            "prompt_tokens": 1523,
            "completion_tokens": 256,
            "total_tokens": 1779,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 42.27465447900502
        },
        {
          "kind": "prefill-1",
          "wall_s": 3.548157937999349,
          "ttft_s": 0.03152319497894496,
          "usage": {
            "prompt_tokens": 1523,
            "completion_tokens": 256,
            "total_tokens": 1779,
            "prompt_tokens_details": {
              "cached_tokens": 1522
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 72.1501140798561
        },
        {
          "kind": "prefill-2",
          "wall_s": 3.22521312898607,
          "ttft_s": 0.030915000999812037,
          "usage": {
            "prompt_tokens": 1523,
            "completion_tokens": 237,
            "total_tokens": 1760,
            "prompt_tokens_details": {
              "cached_tokens": 1522
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 73.48351582411769
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.023184175981441513,
        "first_request_ttft_s": 0.5000449980143458,
        "cached_prompt_tokens": [
          0,
          29,
          29
        ],
        "median_wall_s": 3.3077639779949095,
        "median_completion_tokens_per_end_to_end_s": 77.39367188924444,
        "actual_prompt_tokens": [
          30,
          30,
          30
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.03152319497894496,
        "first_request_ttft_s": 2.4318677200062666,
        "cached_prompt_tokens": [
          0,
          1522,
          1522
        ],
        "median_wall_s": 3.548157937999349,
        "median_completion_tokens_per_end_to_end_s": 72.1501140798561,
        "actual_prompt_tokens": [
          1523,
          1523,
          1523
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": true
    },
    {
      "id": "minicpmv-mix_q3gud_im-reserve1024",
      "label": "MiniCPM-V 4.7 \u00b7 text only",
      "quant": "mix_q3gud_im",
      "status": "completed",
      "wall_s": 908.299976743001,
      "model_source": {
        "repository": "openbmb/MiniCPM-V-4.7-35B-A3B-gguf",
        "revision": "77f6d8cb08b2b115ce27d2e2ac1359e126921689",
        "files": [
          {
            "filename": "MiniCPM-V-4_7-35B-A3B-mix_q3gud_im.gguf",
            "bytes": 15503944928,
            "sha256": "6bfeefbfc723ab6fe557fcea28b31253e14128efe8d8d5774e3256a547b3a946"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {}
      },
      "initial_expert_profile_sha256": "89c6bdd9153efa8c0b2937aab9669cf07de0ff88fa0ffaee5a8d28ec9032ddab",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 0,
      "business_scheduled": 6,
      "business_wilson95": [
        2.7755575615628914e-17,
        0.3903342879021653
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.22712418300653595,
      "coding_passes": 2,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.15003898915214947,
        0.8499610108478506
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": true,
      "transport_errors": 0,
      "gpu_fault_detected": false,
      "context_window_rejections": [],
      "startup_wall_s": 25.687214564997703,
      "resources": {
        "samples": 181,
        "observed_peak_vram_bytes": 11803344896,
        "guest_peak_cgroup_memory_bytes": 29848752128,
        "observed_min_free_vram_bytes": 1064779776,
        "maximum_available_gpu_sensor_c": 87.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 17.14344726499985,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 5405,
          "recorded_completion_tokens": 626,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 19.6256508139777,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 6420,
          "recorded_completion_tokens": 952,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.3333333333333333,
          "terminal": "final_answer",
          "wall_s": 45.757068661012454,
          "tool_calls": 12,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 51761,
          "recorded_completion_tokens": 1830,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.5294117647058824,
          "terminal": "final_answer",
          "wall_s": 99.38409278998733,
          "tool_calls": 26,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "gmail_message_not_sent_to",
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains",
            "hubspot_contact_not_exists"
          ],
          "http_error_status": null,
          "model_calls": 9,
          "recorded_prompt_tokens": 55872,
          "recorded_completion_tokens": 5701,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 118.64034664200153,
          "tool_calls": 43,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 4,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 318914,
          "recorded_completion_tokens": 3566,
          "empty_responses": 0
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 139.0177303889941,
          "tool_calls": 25,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 160114,
          "recorded_completion_tokens": 6699,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": false,
          "partial_credit": 0.5,
          "terminal": "final_answer",
          "wall_s": 117.54521788400598,
          "tool_calls": 21,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 5,
          "failed_assertion_types": [
            "gmail_message_not_sent_to"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 109154,
          "recorded_completion_tokens": 6626,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 97.62487769100699,
          "tool_calls": 20,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 3,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains",
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 142380,
          "recorded_completion_tokens": 4284,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 6.14498840100714,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 37.1735787820071,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 43,
          "wall_s": 70.82987448500353,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 42,
          "wall_s": 73.04603985301219,
          "finish_reason": "length"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 4.664880329015432,
          "ttft_s": 0.35650295700179413,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 54.87814947956688
        },
        {
          "kind": "generation-1",
          "wall_s": 4.363873029011302,
          "ttft_s": 0.021410968009149656,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 58.66348500474142
        },
        {
          "kind": "generation-2",
          "wall_s": 4.369549707975239,
          "ttft_s": 0.021555248997174203,
          "usage": {
            "prompt_tokens": 29,
            "completion_tokens": 256,
            "total_tokens": 285,
            "prompt_tokens_details": {
              "cached_tokens": 28
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 58.58727262737223
        },
        {
          "kind": "prefill-0",
          "wall_s": 6.080826495977817,
          "ttft_s": 1.6618892010010313,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 42.09954027948866
        },
        {
          "kind": "prefill-1",
          "wall_s": 4.4468403540086,
          "ttft_s": 0.022210971015738323,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 57.56896574198555
        },
        {
          "kind": "prefill-2",
          "wall_s": 4.445703280012822,
          "ttft_s": 0.022774112003389746,
          "usage": {
            "prompt_tokens": 1522,
            "completion_tokens": 256,
            "total_tokens": 1778,
            "prompt_tokens_details": {
              "cached_tokens": 1521
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 57.58369011061433
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.021555248997174203,
        "first_request_ttft_s": 0.35650295700179413,
        "cached_prompt_tokens": [
          0,
          28,
          28
        ],
        "median_wall_s": 4.369549707975239,
        "median_completion_tokens_per_end_to_end_s": 58.58727262737223,
        "actual_prompt_tokens": [
          29,
          29,
          29
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.022774112003389746,
        "first_request_ttft_s": 1.6618892010010313,
        "cached_prompt_tokens": [
          0,
          1521,
          1521
        ],
        "median_wall_s": 4.4468403540086,
        "median_completion_tokens_per_end_to_end_s": 57.56896574198555,
        "actual_prompt_tokens": [
          1522,
          1522,
          1522
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": true
    },
    {
      "id": "lfm25-ud-q4_k_xl-reserve1024",
      "label": "LFM2.5 24B-A2B",
      "quant": "UD-Q4_K_XL",
      "status": "completed",
      "wall_s": 681.283686417999,
      "model_source": {
        "repository": "unsloth/LFM2.5-24B-A2B-GGUF",
        "revision": "faa77113e93335b63423e9e8d33395f86eaf8946",
        "files": [
          {
            "filename": "LFM2.5-24B-A2B-UD-Q4_K_XL.gguf",
            "bytes": 14876901632,
            "sha256": "a235d23638cc5549cb1ff61da7522c8a7e97f056f27093462a1e56f35aba91d8"
          }
        ]
      },
      "engine_settings": {
        "max-context": "65536",
        "threads": "8",
        "conversation-cache-mib": "0",
        "vram-reserve-mib": "1024",
        "kv-whole": true,
        "quality_reasoning_budget_tokens": 512,
        "quality_request_overrides": {}
      },
      "initial_expert_profile_sha256": "594ea439eebd74265f0679bba99c0a94b8a4cf3a8ae9852c4ef895fa0ff32e82",
      "inference_image_id": "sha256:3273611332bfcb24e8421ac4d9cf7822b3ef638795f87b91083706e5d62e4336",
      "observed_container_limits": {
        "Memory": 27917287424,
        "MemorySwap": 27917287424,
        "NanoCpus": 9000000000,
        "ReadonlyRootfs": true,
        "NetworkMode": "none",
        "CapDrop": [
          "ALL"
        ],
        "SecurityOpt": [
          "no-new-privileges:true"
        ]
      },
      "basic_passes": 2,
      "basic_scheduled": 2,
      "business_passes": 1,
      "business_scheduled": 6,
      "business_wilson95": [
        0.030053369748306635,
        0.5635028221864702
      ],
      "business_valid_evaluations": 6,
      "business_partial_mean": 0.25,
      "coding_passes": 1,
      "coding_scheduled": 4,
      "coding_wilson95": [
        0.04558726080970055,
        0.6993581574175981
      ],
      "coding_valid_evaluations": 4,
      "valid_grading": true,
      "runtime_healthy": true,
      "transport_errors": 0,
      "gpu_fault_detected": false,
      "context_window_rejections": [],
      "startup_wall_s": 15.531470613001147,
      "resources": {
        "samples": 137,
        "observed_peak_vram_bytes": 11825393664,
        "guest_peak_cgroup_memory_bytes": 29135466496,
        "observed_min_free_vram_bytes": 1042731008,
        "maximum_available_gpu_sensor_c": 84.0,
        "guest_oom_event_delta": {
          "oom": 0,
          "oom_kill": 0
        },
        "note": "Five-second point sampling; includes hotspot when exposed. Brief peaks may be missed. Guest cgroup RAM includes filesystem cache and is not an anonymous model-RAM requirement."
      },
      "automation": [
        {
          "id": "simple.asana_board_presentation",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 12.554830765991937,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 4688,
          "recorded_completion_tokens": 536,
          "empty_responses": 0
        },
        {
          "id": "simple.gcal_weekly_standup",
          "domain": "simple",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "final_answer",
          "wall_s": 19.89612276299158,
          "tool_calls": 2,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 3,
          "recorded_prompt_tokens": 6773,
          "recorded_completion_tokens": 1234,
          "empty_responses": 0
        },
        {
          "id": "sales.demo_scheduling",
          "domain": "sales",
          "strict_pass": false,
          "partial_credit": 0.5,
          "terminal": "final_answer",
          "wall_s": 55.10098854501848,
          "tool_calls": 11,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "slack_message_exists",
            "zoom_meeting_exists"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 48980,
          "recorded_completion_tokens": 3161,
          "empty_responses": 0
        },
        {
          "id": "marketing.referral_processing",
          "domain": "marketing",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 84.64367366599618,
          "tool_calls": 11,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_message_sent_to",
            "gmail_message_sent_to_with_body_contains",
            "hubspot_contact_exists"
          ],
          "http_error_status": null,
          "model_calls": 9,
          "recorded_prompt_tokens": 49869,
          "recorded_completion_tokens": 5844,
          "empty_responses": 0
        },
        {
          "id": "operations.docusign_annual_review",
          "domain": "operations",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 78.91176595300203,
          "tool_calls": 25,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "confluence_action_exists",
            "docusign_envelope_from_template",
            "docusign_envelope_has_signer",
            "monday_action_exists",
            "slack_message_exists",
            "zoom_action_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 191336,
          "recorded_completion_tokens": 4147,
          "empty_responses": 0
        },
        {
          "id": "support.hiver_workload_forecast",
          "domain": "support",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "step_limit",
          "wall_s": 63.35785664099967,
          "tool_calls": 34,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 0,
          "failed_assertion_types": [
            "gmail_email_body_contains",
            "gmail_message_sent_to",
            "google_sheets_row_count",
            "google_sheets_row_exists"
          ],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 173143,
          "recorded_completion_tokens": 3309,
          "empty_responses": 0
        },
        {
          "id": "finance.wave_client_statement",
          "domain": "finance",
          "strict_pass": true,
          "partial_credit": 1.0,
          "terminal": "step_limit",
          "wall_s": 118.39881447399966,
          "tool_calls": 28,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 3,
          "failed_assertion_types": [],
          "http_error_status": null,
          "model_calls": 16,
          "recorded_prompt_tokens": 269718,
          "recorded_completion_tokens": 5610,
          "empty_responses": 0
        },
        {
          "id": "hr.salary_band_audit",
          "domain": "hr",
          "strict_pass": false,
          "partial_credit": 0.0,
          "terminal": "final_answer",
          "wall_s": 41.16812263298198,
          "tool_calls": 10,
          "tool_execution_errors": 0,
          "grading_error": false,
          "tool_returned_errors": 1,
          "failed_assertion_types": [
            "gmail_message_sent_to_with_body_contains",
            "google_sheets_row_updated"
          ],
          "http_error_status": null,
          "model_calls": 8,
          "recorded_prompt_tokens": 38288,
          "recorded_completion_tokens": 3075,
          "empty_responses": 0
        }
      ],
      "coding": [
        {
          "id": "atcoder|abc400_a",
          "difficulty": "easy",
          "pass_at_1": true,
          "failure_reason": null,
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 8.94256904401118,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|abc387_c",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 43,
          "wall_s": 49.49219015499693,
          "finish_reason": "length"
        },
        {
          "id": "atcoder|arc191_a",
          "difficulty": "medium",
          "pass_at_1": false,
          "failure_reason": "wrong_answer",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": false,
          "tests_scheduled": 43,
          "wall_s": 49.091406513005495,
          "finish_reason": "stop"
        },
        {
          "id": "atcoder|arc193_a",
          "difficulty": "hard",
          "pass_at_1": false,
          "failure_reason": "no_code_block",
          "generation_error": false,
          "grader_error": false,
          "extraction_failed": true,
          "tests_scheduled": 42,
          "wall_s": 51.047777052008314,
          "finish_reason": "length"
        }
      ],
      "speed": [
        {
          "kind": "generation-0",
          "wall_s": 3.9279337170009967,
          "ttft_s": 0.3263305379950907,
          "usage": {
            "prompt_tokens": 28,
            "completion_tokens": 256,
            "total_tokens": 284,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 65.1742158713049
        },
        {
          "kind": "generation-1",
          "wall_s": 3.104336604999844,
          "ttft_s": 0.034487430995795876,
          "usage": {
            "prompt_tokens": 28,
            "completion_tokens": 256,
            "total_tokens": 284,
            "prompt_tokens_details": {
              "cached_tokens": 27
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 82.46528407637446
        },
        {
          "kind": "generation-2",
          "wall_s": 3.0533629629935604,
          "ttft_s": 0.03140225398237817,
          "usage": {
            "prompt_tokens": 28,
            "completion_tokens": 256,
            "total_tokens": 284,
            "prompt_tokens_details": {
              "cached_tokens": 27
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 83.84198115412194
        },
        {
          "kind": "prefill-0",
          "wall_s": 4.543989634985337,
          "ttft_s": 1.3336507409985643,
          "usage": {
            "prompt_tokens": 1521,
            "completion_tokens": 256,
            "total_tokens": 1777,
            "prompt_tokens_details": {
              "cached_tokens": 0
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 56.338156678217445
        },
        {
          "kind": "prefill-1",
          "wall_s": 3.094044376979582,
          "ttft_s": 0.03716979798628017,
          "usage": {
            "prompt_tokens": 1521,
            "completion_tokens": 256,
            "total_tokens": 1777,
            "prompt_tokens_details": {
              "cached_tokens": 1520
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 82.73960189604914
        },
        {
          "kind": "prefill-2",
          "wall_s": 3.1321701539854985,
          "ttft_s": 0.040615553996758536,
          "usage": {
            "prompt_tokens": 1521,
            "completion_tokens": 256,
            "total_tokens": 1777,
            "prompt_tokens_details": {
              "cached_tokens": 1520
            }
          },
          "error": null,
          "completion_tokens_per_end_to_end_s": 81.73246899573938
        }
      ],
      "speed_generation": {
        "requests": 3,
        "median_ttft_s": 0.034487430995795876,
        "first_request_ttft_s": 0.3263305379950907,
        "cached_prompt_tokens": [
          0,
          27,
          27
        ],
        "median_wall_s": 3.104336604999844,
        "median_completion_tokens_per_end_to_end_s": 82.46528407637446,
        "actual_prompt_tokens": [
          28,
          28,
          28
        ]
      },
      "speed_prefill": {
        "requests": 3,
        "median_ttft_s": 0.040615553996758536,
        "first_request_ttft_s": 1.3336507409985643,
        "cached_prompt_tokens": [
          0,
          1520,
          1520
        ],
        "median_wall_s": 3.1321701539854985,
        "median_completion_tokens_per_end_to_end_s": 81.73246899573938,
        "actual_prompt_tokens": [
          1521,
          1521,
          1521
        ]
      },
      "advisory_business_advance": false,
      "advisory_coding_advance": false
    }
  ],
  "hardware": {
    "gpu": "AMD Radeon RX 6700 XT",
    "vram_marketed_gb": 12,
    "cpu": "Ryzen 5 3600",
    "system_ram_installed_gb": 32
  },
  "runtime": {
    "name": "PolyStrata strata-poly HIP gfx1031",
    "version": "0.1.45",
    "commit": "26e4cb5df7996edfb5ff549a63b82d8581e1e658"
  },
  "sandbox": {
    "guest_memory_gib": 28,
    "guest_swap_gib": 0,
    "inference_memory_gib": 26,
    "inference_cpu_quota": 9,
    "client_and_scorer_memory_mib": 1536,
    "client_and_scorer_cpu_quota": 1,
    "network": "offline; loopback-only inference clients",
    "nonroot": true
  },
  "evaluation_environment": {
    "image_id": "sha256:0447630d30641a49ff4020e95b16ba8f412e935e6efc27a69f0c734b6b122fb9",
    "python": "Python 3.13.16",
    "packages": [
      "aiohappyeyeballs==2.7.1",
      "aiohttp==3.14.5",
      "aiosignal==1.4.0",
      "annotated-types==0.8.0",
      "anthropic==1.15.0",
      "anyio==4.15.1",
      "attrs==26.1.0",
      "click==8.5.0",
      "datasets==5.1.0",
      "dill==0.4.1",
      "docstring_parser==0.18.0",
      "filelock==4.2.4",
      "frozenlist==1.8.0",
      "fsspec==2026.7.0",
      "h11==0.16.0",
      "hf-xet==1.7.0",
      "httpcore2==2.15.1",
      "httpx2==2.15.1",
      "huggingface_hub==2.2.0",
      "idna==3.20",
      "jiter==0.17.0",
      "multidict==7.1.0",
      "multiprocess==0.70.19",
      "numpy==2.5.4",
      "openai==3.35.1",
      "opentelemetry-api==1.45.1",
      "packaging==26.3",
      "pandas==3.0.6",
      "propcache==0.5.4",
      "pyarrow==26.0.0",
      "pydantic==2.14.1",
      "pydantic_core==2.50.1",
      "python-dateutil==2.9.0.post0",
      "PyYAML==6.0.3",
      "six==1.17.0",
      "sniffio==1.3.1",
      "tqdm==4.70.1",
      "truststore==0.10.5",
      "typing-inspection==0.4.4",
      "typing_extensions==4.16.0",
      "xxhash==4.0.2",
      "yarl==1.25.1"
    ]
  },
  "post_run_backend_control": {
    "status": "passed",
    "scope": "Postflight diagnostic, not a scored benchmark task",
    "gmail_simulator_and_upstream_rubric_positive_control": true,
    "untouched_world_negative_control": true,
    "wrong_content_negative_control": true,
    "real_messages_sent": 0
  },
  "costs": {
    "cloud_inference_scoring_usd": 0,
    "electricity_usd": null,
    "hardware_depreciation_usd": null,
    "labor_usd": null,
    "total_usd": null,
    "scope": "Candidate inference and scoring only. Setup assistant, hosting, electricity, depreciation and labor were not priced."
  },
  "private_frozen_task_manifest_sha256": "a88f1a3e43977c96baf1f6c4a9f1e13f5012bfa40ff20694771506b6b583d3e4",
  "sources": {
    "automation_commit": "4a8e1061254004d9dac807054eed33fad7d1ff14",
    "lcb_commit": "28fef95ea8c9f7a547c8329f2cd3d32b92c1fa24",
    "lcb_dataset": {
      "repository": "livecodebench/code_generation_lite",
      "revision": "0fe84c3912ea0c4d4a78037083943e8f0c4dd505",
      "config": "v6",
      "file": "test6.jsonl",
      "sha256": "bb4c364f71921c4495a6ad15abe1a927350b720009f4933e2e71f8af0f6fd1f5",
      "rows": 175,
      "earliest_date": "2025-01-04T00:00:00",
      "latest_date": "2025-04-06T00:00:00"
    }
  },
  "caveats": [
    "Small fixed public subsets; not official leaderboard scores or a reliable fine ranking.",
    "AutomationBench final-state completion rates are not directly comparable to the earlier v2.1 practical rubric or HumanEval+ percentages.",
    "Wilson intervals describe small binary counts; the fixed, stratified tasks are not a random sample of all real business work.",
    "No guarantee against training contamination; model training cutoffs unknown.",
    "The four frozen Quick Screen coding problems are all AtCoder; selection was stratified by difficulty, not platform.",
    "Simple tasks excluded from business denominator. All-test coding pass@1, one attempt.",
    "Speed is completion tokens divided by total request wall time, not pure decode throughput.",
    "Fixed repeated speed prompts may reuse engine KV/prefix state. Long-prompt latency is a warm-session measurement, not isolated cold prefill.",
    "Automation toolset api; 16 response steps, 180 seconds per task, 2048 output tokens.",
    "Quick Screen limits are stricter than upstream defaults; failures do not establish inability with a longer budget or a different agent.",
    "Coding 180 seconds generation, 4096 output tokens; offline grading 6 seconds/test and 180 seconds/problem.",
    "No external API credentials: upstream simulated tool fallbacks apply.",
    "Gemma thinking disabled on every request; other quality profiles retain prior settings.",
    "Results measure complete model/quant/runtime/agent configurations, including native draft and tail-skip settings; they are not weights-only comparisons.",
    "An invalid pilot with additional argument validation was preserved and excluded; all scored runs use corrected v3.0.1 dispatch.",
    "Accepted requests and responses are archived. Failed HTTP responses have error summaries; their response bodies were not captured.",
    "Tier 2 and Full Validation have not been run."
  ],
  "task_manifest_sha256": "27bd2fe18ab5efd59f345d01e1434db953b275b441e1ef354be68ababd8124b3"
}