{"apiVersion":"v1","evaluationSchemaVersion":"1.0.0","kind":"owner_reported_claim","record":{"id":"glm-5-2-mcp-atlas-public-owner-reported","claimType":"owner_reported","modelId":"glm-5-2","modelName":"GLM-5.2","owner":"Z.ai","artifact":{"repository":"zai-org/GLM-5.2","revision":"b4734de4facf877f85769a911abafc5283eab3d9"},"artifactAssociation":"artifact_snapshot_associated","executionArtifactDigest":null,"benchmark":{"suite":"MCP-Atlas","version":null,"subset":"500-task public set"},"metric":{"name":"owner-reported score","value":76.8,"unit":"reported_score","scale":"0-100 as presented","direction":"higher_is_better"},"evaluation":{"mode":"thinking","reportedSettings":[{"name":"thinking_mode","value":true},{"name":"task_count","value":500},{"name":"timeout_seconds","value":600},{"name":"judge_model","value":"Gemini-3.0-Pro"}]},"sourceRefs":[{"sourceId":"glm-5-2-pinned-model-card","locator":"Benchmark table, MCP-Atlas Public Set row; Footnote MCP-Atlas settings"}],"comparisonEligible":false,"missingContext":["The owner does not explicitly define the metric or label the score as a percentage.","Exact reasoning effort, temperature, context limit, harness version, and tool configuration are not reported.","Sample count per task, aggregation method, and inference hardware are not reported.","The provider does not publish a digest of the tensor artifact used for the evaluation."]},"sources":[{"id":"glm-5-2-pinned-model-card","title":"GLM-5.2 pinned model card","publisher":"Z.ai","url":"https://huggingface.co/zai-org/GLM-5.2/blob/b4734de4facf877f85769a911abafc5283eab3d9/README.md","retrievedAt":"2026-08-03","sourceType":"official_model_card","artifactSnapshot":{"repository":"zai-org/GLM-5.2","revision":"b4734de4facf877f85769a911abafc5283eab3d9"}}],"rawArtifacts":[]}