{"apiVersion":"v1","evaluationSchemaVersion":"1.0.0","kind":"owner_reported_claim","record":{"id":"glm-5-2-swe-bench-pro-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":"SWE-bench Pro","version":null,"subset":null},"metric":{"name":"owner-reported score","value":62.1,"unit":"reported_score","scale":"0-100 as presented","direction":"higher_is_better"},"evaluation":{"mode":"unspecified","reportedSettings":[{"name":"framework","value":"OpenHands"},{"name":"prompt_variant","value":"tailored instruction prompt"},{"name":"temperature","value":1},{"name":"top_p","value":1},{"name":"max_new_tokens","value":32000},{"name":"context_tokens","value":400000}]},"sourceRefs":[{"sourceId":"glm-5-2-pinned-model-card","locator":"Benchmark table, SWE-bench Pro row; Footnote SWE-Bench Pro settings"}],"comparisonEligible":false,"missingContext":["The owner does not explicitly define the metric or label the score as a percentage.","OpenHands version and the tailored instruction prompt are not published.","Dataset commit, container images, task count, trials, and aggregation method are not reported.","Inference hardware is 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":[]}