{
  "created_at": "2026-09-22T02:30:51.120480Z",
  "dataset": "princeton-nlp/SWE-bench_Verified",
  "endpoint": {
    "base_url": "http://127.0.0.1:<redacted-port>/v1",
    "model": "glm53-flash-exl3-4bpw-v84-fp8-tp2-c4-327k-r10-vision8-apc-nospec"
  },
  "failure": null,
  "harnesses": {
    "agent": {
      "name": "mini-swe-agent",
      "revision": "a83fcae82d2a08f0ee0c688f9d137b3566c097f8"
    },
    "grader": {
      "name": "swe-bench",
      "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
    },
    "python_environment": {
      "architecture": "x86_64",
      "platform": "linux",
      "python": {
        "implementation": "CPython",
        "version": "3.14.4"
      },
      "resolved_packages_sha256": "809336a2a74041fa07adad60eaca2208acd936f3728d2368d22f98657576a37a",
      "schema": "anvil-serving.swe-python-environment/v1"
    }
  },
  "instances": [
    {
      "duration_s": null,
      "exit_status": "Submitted",
      "failure_class": null,
      "grader": {
        "completed": true,
        "name": "swe-bench",
        "report_sha256": "d57441deae4a3a57528b237c4ec092d20b7af30db94cc77d3b92f71fbe466613",
        "resolved": false,
        "revision": "f7bbbb2ccdf479001d6467c9e34af59e44a840f9"
      },
      "instance_id": "psf__requests-2317",
      "prediction_sha256": "1f4f0467206173ae3f6fa344e94834d407185f0da89336a816a54cd7435af8f2",
      "prompt_identity": {
        "dataset": "princeton-nlp/SWE-bench_Verified",
        "split": "test"
      },
      "request_ids": [
        "chatcmpl-82e4ac8580615068",
        "chatcmpl-8448616b9ec5e98f",
        "chatcmpl-85da4808fd136c02",
        "chatcmpl-88bda80cef2a7461",
        "chatcmpl-8bf136dadead0c34",
        "chatcmpl-927ccdbf68bbe066",
        "chatcmpl-9820cc16b86e055e",
        "chatcmpl-9929e0533353c959",
        "chatcmpl-9f1deefb4ae2fa6b",
        "chatcmpl-a638d25419c6eb8b",
        "chatcmpl-a7a20de109d6e674",
        "chatcmpl-a7ae8c8996b0ec95",
        "chatcmpl-a8b529c88b7908ee",
        "chatcmpl-ab69ddd8db6461be",
        "chatcmpl-ac1e0492e52a128b",
        "chatcmpl-af0fbc41c48d3683",
        "chatcmpl-b1d63cb302abf23a",
        "chatcmpl-b64c03c8ad2fb813",
        "chatcmpl-b802378d62c8934b",
        "chatcmpl-b8cc9fa49e375fd6",
        "chatcmpl-bc399b4a6af0747b",
        "chatcmpl-bca33bc8ff520da5",
        "chatcmpl-bf5b6f2ea32dd88b",
        "chatcmpl-bf60810f816ff137"
      ],
      "tokens": {
        "completion_tokens": null,
        "prompt_tokens": null,
        "total_tokens": null
      },
      "trajectory": {
        "path": "private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/mini-output/psf__requests-2317/psf__requests-2317.traj.json",
        "sha256": "0f7735ea7d78bed195d87293957b9a41102e84f1088c51d16ac5fd1a5388f431"
      }
    }
  ],
  "official_grader_complete": true,
  "ownership_id": "mimo-v26-campaign",
  "plan_sha256": "1200e7d710db244d4282b4c77af84764fd6ed6624ebc5c9d336f2ec7ede4c79e",
  "profile": "smoke",
  "profile_sha256": "090745451099214af7c222f736769737911453fe9e9c5d14ffc04f5a4a3e4586",
  "promotion": {
    "authorized": false,
    "message": "Benchmark evidence does not authorize model promotion."
  },
  "request_controls": {
    "reasoning_effort": null,
    "sampling": {
      "temperature": {
        "effective_request": 0.0,
        "requested": 0.0,
        "sent": true
      },
      "top_p": {
        "effective_request": null,
        "requested": null,
        "sent": false
      }
    },
    "thinking_mode": "enabled"
  },
  "run_id": "glm-mimo-swe-smoke",
  "schema": "anvil-serving.swe-run/v1",
  "selection": {
    "instance_ids": [
      "psf__requests-2317"
    ],
    "kind": "explicit_instance_ids",
    "sha256": "62a72708eb956865ca7c4f26fc97591fca5efa60b0b596236b3fccc168b0ee73"
  },
  "split": "test",
  "stages": [
    {
      "command": [
        "private-campaign/operator-home/benchmark-harness-cache/swe-python-environments/0bc9301c810a0e8f810569f10c082a8a03cc81a7b87fbc0cdd868ce30c27ff93/bin/python",
        "private-campaign/operator-home/benchmark-harness-cache/mini-swe-agent/a83fcae82d2a08f0ee0c688f9d137b3566c097f8/src/minisweagent/run/benchmarks/swebench.py",
        "--output",
        "private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/mini-output",
        "--model",
        "openai/glm53-flash-exl3-4bpw-v84-fp8-tp2-c4-327k-r10-vision8-apc-nospec",
        "--subset",
        "verified",
        "--split",
        "test",
        "--filter",
        "^(?:psf__requests\\-2317)$",
        "--workers",
        "1",
        "--environment-class",
        "docker",
        "--config",
        "private-campaign/operator-home/benchmark-harness-cache/mini-swe-agent/a83fcae82d2a08f0ee0c688f9d137b3566c097f8/src/minisweagent/config/benchmarks/swebench.yaml",
        "--config",
        "private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/anvil-swe-config.yaml"
      ],
      "duration_s": 290.317751,
      "name": "agent",
      "output_truncated": false,
      "returncode": 0,
      "status": "completed",
      "stderr": "Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.\n",
      "stdout": "minisweagent: INFO: Results will be saved to                                    \nprivate-campaign/operator-home/benchm\nark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/mini-output                  \nLogging to 'private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/mini-output/minisweagent.log'\nminisweagent: INFO: Loading dataset princeton-nlp/SWE-Bench_Verified, split     \ntest...                                                                         \nminisweagent: INFO: Instance filter: 500 -> 1 instances                         \nminisweagent: INFO: Running on 1 instances...                                   \nminisweagent: INFO: Building agent config from specs:                           \n['private-campaign/operator-home/benc\nhmark-harness-cache/mini-swe-agent/a83fcae82d2a08f0ee0c688f9d137b3566c097f8/src/\nminisweagent/config/benchmarks/swebench.yaml',                                  \n'private-campaign/operator-home/bench\nmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/anvil-swe-config.yaml']     \nminisweagent.environment: DEBUG: Starting container with command:               \n/usr/bin/docker run -d --name REDACTED_CONTAINER_NAME -w /testbed --platform      \nlinux/amd64 --network none --rm                                                 \ndocker.io/swebench/sweb.eval.x86_64.psf_1776_requests-2317:latest sleep 2h      \nminisweagent.environment: INFO: Started container REDACTED_CONTAINER_NAME with ID \nREDACTED_CONTAINER_ID                \nminisweagent: INFO: Saved trajectory to                                         \n'private-campaign/operator-home/bench\nmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/mini-output/psf__requests-23\n17/psf__requests-2317.traj.json'                                                \n  Overall Progress ($0.00) ━━━━━━━━━━━━━━━━━━━━━━━ 1/1 100% 0:04:47 eta: 0:00:00\n┏━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n┃ Exit Status ┃ Count ┃ Most recent instances                                  ┃\n┡━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n│ Submitted   │     1 │ psf__requests-2317                                     │\n└─────────────┴───────┴────────────────────────────────────────────────────────┘"
    },
    {
      "command": [
        "private-campaign/operator-home/benchmark-harness-cache/swe-python-environments/0bc9301c810a0e8f810569f10c082a8a03cc81a7b87fbc0cdd868ce30c27ff93/bin/python",
        "-m",
        "swebench.harness.run_evaluation",
        "--dataset_name",
        "princeton-nlp/SWE-bench_Verified",
        "--split",
        "test",
        "--predictions_path",
        "private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/predictions.jsonl",
        "--max_workers",
        "1",
        "--run_id",
        "glm-mimo-swe-smoke",
        "--timeout",
        "1800",
        "--report_dir",
        "private-campaign/operator-home/benchmark-runs/mimo-v26-campaign/glm-mimo-swe-smoke/work/official-grader",
        "--instance_ids",
        "psf__requests-2317"
      ],
      "duration_s": 1174.407809,
      "name": "official_grader",
      "output_truncated": false,
      "returncode": 0,
      "status": "completed",
      "stderr": "private-campaign/operator-home/benchmark-harness-cache/swe-bench/f7bbbb2ccdf479001d6467c9e34af59e44a840f9/swebench/harness/run_evaluation.py:270: SyntaxWarning: 'return' in a 'finally' block\n  return {\n<frozen runpy>:128: RuntimeWarning: 'swebench.harness.run_evaluation' found in sys.modules after import of package 'swebench.harness', but prior to execution of 'swebench.harness.run_evaluation'; this may result in unpredictable behaviour\n2026-09-21 19:35:42,094 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/main/README.md \"HTTP/1.1 307 Temporary Redirect\"\n2026-09-21 19:35:42,177 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/datasets/princeton-nlp/SWE-bench_Verified/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/README.md?%2Fdatasets%2Fprinceton-nlp%2FSWE-bench_Verified%2Fresolve%2Fmain%2FREADME.md=&etag=%22f362a6ce9579a3ee1922e3402463feef139b7d00%22 \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:42,263 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/SWE-bench_Verified.py \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:42,520 - httpx - INFO - HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/princeton-nlp/SWE-bench_Verified/princeton-nlp/SWE-bench_Verified.py \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:42,608 - httpx - INFO - HTTP Request: GET https://huggingface.co/api/datasets/princeton-nlp/SWE-bench_Verified/revision/c104f840cc67f8b6eec6f759ebc8b2693d585d4a \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:42,695 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/.huggingface.yaml \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:42,814 - httpx - INFO - HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=princeton-nlp/SWE-bench_Verified \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:42,901 - httpx - INFO - HTTP Request: GET https://huggingface.co/api/datasets/princeton-nlp/SWE-bench_Verified/tree/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/data?recursive=true&expand=false \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:42,984 - httpx - INFO - HTTP Request: GET https://huggingface.co/api/datasets/princeton-nlp/SWE-bench_Verified/tree/c104f840cc67f8b6eec6f759ebc8b2693d585d4a?recursive=false&expand=false \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:43,071 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/dataset_infos.json \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:43,180 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/main/README.md \"HTTP/1.1 307 Temporary Redirect\"\n2026-09-21 19:35:43,195 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/api/resolve-cache/datasets/princeton-nlp/SWE-bench_Verified/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/README.md?%2Fdatasets%2Fprinceton-nlp%2FSWE-bench_Verified%2Fresolve%2Fmain%2FREADME.md=&etag=%22f362a6ce9579a3ee1922e3402463feef139b7d00%22 \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:43,276 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/SWE-bench_Verified.py \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:43,362 - httpx - INFO - HTTP Request: HEAD https://s3.amazonaws.com/datasets.huggingface.co/datasets/datasets/princeton-nlp/SWE-bench_Verified/princeton-nlp/SWE-bench_Verified.py \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:43,451 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/.huggingface.yaml \"HTTP/1.1 404 Not Found\"\n2026-09-21 19:35:43,547 - httpx - INFO - HTTP Request: GET https://datasets-server.huggingface.co/info?dataset=princeton-nlp/SWE-bench_Verified \"HTTP/1.1 200 OK\"\n2026-09-21 19:35:43,628 - httpx - INFO - HTTP Request: HEAD https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified/resolve/c104f840cc67f8b6eec6f759ebc8b2693d585d4a/dataset_infos.json \"HTTP/1.1 404 Not Found\"\n\rEvaluation:   0%|          | 0/1 [00:00<?, ?it/s, error=0, ✓=0, ✖=0]\rEvaluation:   0%|          | 0/1 [19:27<?, ?it/s, ✓=0, ✖=1, error=0]\rEvaluation: 100%|██████████| 1/1 [19:27<00:00, 1167.62s/it, ✓=0, ✖=1, error=0]\rEvaluation: 100%|██████████| 1/1 [19:27<00:00, 1167.62s/it, ✓=0, ✖=1, error=0]\n",
      "stdout": "Found 1 existing instance images. Will reuse them.\nRunning 1 instances...\nAll instances run.\nCleaning cached images...\nRemoved 0 images.\nTotal instances: 1\nInstances submitted: 1\nInstances completed: 1\nInstances incomplete: 0\nInstances resolved: 0\nInstances unresolved: 1\nInstances with empty patches: 0\nInstances with errors: 0\nUnstopped containers: 0\nUnremoved images: 1\nReport written to openai__glm53-flash-exl3-4bpw-v84-fp8-tp2-c4-327k-r10-vision8-apc-nospec.glm-mimo-swe-smoke.json\n"
    }
  ],
  "state": "completed",
  "summary": {
    "attempted": 1,
    "graded": 1,
    "resolve_rate": 0.0,
    "resolved": 0
  },
  "task_container_network": "none"
}