{"id":"9ff765cd-a34b-4621-b264-020d6d8b7c34","name":"DeepEval","slug":"deepeval","description":"Open-source LLM evaluation framework. Research-backed metrics: G-Eval, hallucination detection, answer relevancy, task completion, faithfulness. Integrates with pytest.","website_url":"https://github.com/confident-ai/deepeval","category":["ai","testing","benchmark"],"score":{"overall":75,"raw":78,"capped":true,"verified":false,"breakdown":{"latency":7,"consistency":8,"doc_quality":7,"error_clarity":7,"auth_simplicity":9,"token_efficiency":8,"first_try_success":7,"response_parseability":9},"source":"prowl_capped","credential_tested":false,"probe_health":{"status":"healthy","up_pct":1.0,"samples":26,"target":"website","p50_latency_ms":360,"last_probed":"2026-05-14T20:27:27.413104+00:00","lookback_hours":24}},"latency":null,"uptime_30d":null,"protocols":["rest"],"auth_type":null,"mcp_manifest_url":null,"openapi_spec_url":null,"verified":false,"claimed":false,"vendor_id":null,"status":"active","profile":null,"pricing":{"license":"MIT/Apache","free_tier":true,"open_source":true,"cost_per_evaluation":0},"last_crawled":"2026-05-11T16:45:22.843278+00:00","last_benchmarked":"2026-04-06T06:05:41.844145+00:00","supports_x402":false,"agent_auth_methods":null,"supports_streaming":false,"has_sandbox":false,"sdks":null,"llms_txt_url":null,"similarity_score":null}