# Model Evaluation Report ## 1. Evaluation decision - System or model: - Version: - Evaluation owner: - Decision this report supports: ## 2. Intended use - Users and environment: - Intended task: - Out-of-scope uses: - Important harms: ## 3. Test evidence - Dataset and version: - Sampling period: - Important groups and conditions: - Leakage controls: - Known test limitations: ## 4. Baseline and metrics | System | Metric | Result | Required threshold | |---|---|---:|---:| | Baseline | | | | | Candidate | | | | ## 5. Error analysis - False-positive patterns: - False-negative patterns: - Largest numerical errors: - Difficult groups or environments: - Robustness tests: ## 6. Operational evaluation - Latency: - Throughput: - Cost: - Reliability: - Human-review workload: ## 7. Decision - Approve / conditional approval / reject: - Required controls: - Monitoring plan: - Re-evaluation trigger: