{
  "id": "glm53-official",
  "title": "GLM-5.3: official model and deployment card",
  "kind": "model",
  "source_type": "official_model_card",
  "summary": "The full GLM-5.3 model card, with serving routes and evaluation notes. Keep it separate from Flash and from quantized community conversions.",
  "runtime": "vLLM / SGLang / Transformers / KTransformers / TokenSpeed",
  "runtime_topics": [
    "vLLM",
    "SGLang",
    "Transformers",
    "KTransformers",
    "TokenSpeed"
  ],
  "hardware_topics": [],
  "platform_topics": [],
  "model_label": "GLM-5.3",
  "model_family": "GLM",
  "model_id": "zai-org/GLM-5.3",
  "model_release_date": null,
  "model_artifact": {
    "id": "zai-org/GLM-5.3",
    "revision": "ba32f8c19c8738e2c57c71798c601d477a7bf844",
    "format": null
  },
  "evidence_state": "source_reported",
  "site_reproduced": false,
  "record_type": "curated_reference",
  "performance_ranking_allowed": false,
  "metrics": null,
  "metrics_status": "site_metrics_unmeasured; attributed_source_figures_in_editorial.reported_results",
  "conditions": {
    "model_revision": "ba32f8c19c8738e2c57c71798c601d477a7bf844",
    "weight_hash": null,
    "runtime_execution_revision": null,
    "input_tokens": null,
    "output_tokens": null,
    "concurrency": null,
    "cache_state": null,
    "quantization": null,
    "speculative_decoding": null,
    "temperature": null,
    "top_p": null
  },
  "reported_setup": {
    "system": null,
    "node_count": null,
    "parallelism": null,
    "kv_dtype": null,
    "context_limit_tokens": null,
    "experiment_date": null
  },
  "test_profiles": [],
  "deployment_options": [],
  "recipe_parameters": null,
  "measurement_scope": "official_capability_and_deployment",
  "notes": [
    "Reasoning effort and conversation handling are documented with the checkpoint.",
    "The card links a separate Ascend deployment route."
  ],
  "limitations": [
    "Published capability evaluations do not demonstrate latency on the reader’s hardware."
  ],
  "comparison_status": "not_comparable",
  "editorial_status": "source_derived_detailed_article",
  "public_benchmark_snapshot": false,
  "source": {
    "publisher": "zai-org",
    "url": "https://huggingface.co/zai-org/GLM-5.3",
    "repository": "zai-org/GLM-5.3",
    "platform": "huggingface",
    "revision": "ba32f8c19c8738e2c57c71798c601d477a7bf844",
    "document_path": "README.md",
    "pinned_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md",
    "report_url": null,
    "document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf",
    "last_commit_at": "2026-10-14T12:22:48.000Z",
    "checked_on": "2026-10-17",
    "metadata_status": "checked"
  },
  "license": {
    "declared_spdx": "other",
    "declared_name": "glm-5.3",
    "scope": "Publisher model-card declaration; inspect the linked LICENSE and artifact-specific terms."
  },
  "editorial": {
    "version": 1,
    "published_on": "2026-10-17",
    "modified_on": "2026-10-17",
    "byline": "Run AI Here editorial",
    "creation_method": "AI-assisted source reading and original editorial synthesis; no independent model execution.",
    "answer": "The full GLM-5.3 model card, with serving routes and evaluation notes. Keep it separate from Flash and from quantized community conversions.",
    "sections": [
      {
        "heading": "Which artifact does this page identify?",
        "paragraphs": [
          "This is the full GLM-5.3 card, separate from Flash and from community quantizations. Its local-serving section includes a distinct Ascend route. Use the exact checkpoint and the selected conversion as separate identities. The companion recipe’s 743B total and 39B active labels belong to that recipe rather than a measured memory receipt."
        ],
        "citations": [
          "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L41"
        ]
      },
      {
        "heading": "What is the correct reasoning configuration?",
        "paragraphs": [
          "The publisher’s controls match the documented low, high and max reasoning-effort levels, defaulting to max. clear_thinking remains a separate chat-template option with a false default. Retaining the default effort matters for benchmark reproduction; enabling clear_thinking for a chat workflow should be recorded as its own configuration choice."
        ],
        "citations": [
          "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L55"
        ]
      },
      {
        "heading": "How much of the published score can be reproduced from a headline?",
        "paragraphs": [
          "The card reports 66.9 on DeepSWE v1.1 and 88.2 on Terminal-Bench 2.1. Their footnotes use different sampling, context and timeout settings. Terminal-Bench 3.0 is another protocol: three rollouts per task, isolated task containers, up to 600 turns and a ten-hour timeout. A score from one task is not a prediction of workstation throughput or another task’s accuracy."
        ],
        "citations": [
          "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L26"
        ]
      },
      {
        "heading": "What should be retained before comparing results?",
        "paragraphs": [
          "Keep the exact task revision, harness, tool policy, reasoning effort, maximum output and treatment of failures. Some published tasks change installation checks or use a fallback score when a run fails. Those decisions are part of the measurement. Read the footnote for the specific benchmark before comparing this card with a report from another author."
        ],
        "citations": [
          "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L58"
        ]
      }
    ],
    "facts": [
      {
        "name": "Reasoning effort",
        "value": "low / high / max; default max",
        "classification": "publisher_declaration",
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L55",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      },
      {
        "name": "HLE-with-tools context / output cap",
        "value": "300000 / 163840 tokens",
        "classification": "publisher_declaration",
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L60",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      },
      {
        "name": "DeepSWE context / timeout",
        "value": "400K tokens / 6 hours",
        "classification": "publisher_declaration",
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L62",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      },
      {
        "name": "Terminal-Bench 3.0 repeats / turns / timeout",
        "value": "3 rollouts / 600 agent turns / 10 hours",
        "classification": "publisher_declaration",
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L64",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      }
    ],
    "reported_results": [
      {
        "label": "DeepSWE v1.1",
        "metric": "DeepSWE",
        "value": 66.9,
        "unit": "reported score",
        "statistic": "reported value",
        "uncertainty": null,
        "conditions": {
          "model": "zai-org/GLM-5.3",
          "model_revision": "ba32f8c19c8738e2c57c71798c601d477a7bf844",
          "hardware": null,
          "executed_runtime_revision": null,
          "input_tokens": null,
          "output_tokens": null,
          "repetitions": null,
          "measurement_scope": "publisher capability evaluation, not local speed",
          "benchmark": "DeepSWE v1.1",
          "harness": "mini-swe-agent",
          "temperature": 0.95,
          "top_p": 1.0,
          "context": "400K",
          "timeout_hours": 6,
          "reasoning_effort": "max"
        },
        "evidence_state": "source_reported",
        "site_reproduced": false,
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L26",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      },
      {
        "label": "Terminal-Bench 2.1",
        "metric": "Terminal_Bench",
        "value": 88.2,
        "unit": "reported score",
        "statistic": "reported value",
        "uncertainty": null,
        "conditions": {
          "model": "zai-org/GLM-5.3",
          "model_revision": "ba32f8c19c8738e2c57c71798c601d477a7bf844",
          "hardware": null,
          "executed_runtime_revision": null,
          "input_tokens": null,
          "output_tokens": null,
          "repetitions": null,
          "measurement_scope": "publisher capability evaluation, not local speed",
          "benchmark": "Terminal-Bench 2.1",
          "harness": "Claude Code 2.1.207",
          "temperature": 1.0,
          "top_p": 1.0,
          "max_new_tokens": 65536,
          "timeout_hours": 6,
          "reasoning_effort": "max"
        },
        "evidence_state": "source_reported",
        "site_reproduced": false,
        "evidence_url": "https://huggingface.co/zai-org/GLM-5.3/blob/ba32f8c19c8738e2c57c71798c601d477a7bf844/README.md#L24",
        "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
      }
    ],
    "source_document_sha256": "ed1c0a4563c437a32f8953d637a1db9bd831de1b24bd3062a5ace9e04340b1cf"
  }
}