{ "run_id": "benchmark_e3047791a92d", "kind": "agent", "dataset_id": "agent-core-v1", "dataset_hash": "sha256:82fd1b84cc2dc2feec0fc67357d64b145dcdf6c44ec2660f182d550e85b9d27f", "status": "completed", "config_snapshot": { "dataset_id": "agent-core-v1", "provider_id": "provider_65fd326edba646e3bc735c25fbf5ffe8", "model": "deepseek-v4-flash", "max_steps": 6, "timeout_seconds": 90, "token_budget": 6000, "repeat": 1, "allow_network": false, "offline": false, "dataset_hash": "sha256:82fd1b84cc2dc2feec0fc67357d64b145dcdf6c44ec2660f182d550e85b9d27f", "dataset_version": "1.0.0", "execution": "real_agent_runtime", "provider_type": "openai_compatible", "scoring_version": "1.0", "permission_policy": "runtime_user_decision", "active_agent_run_id": "run_1230c37a1c2c4559b69cbc4e01b4721b" }, "metrics": { "total_cases": 4, "evaluated_cases": 4, "task_success_rate": 1, "tool_selection_accuracy": 1, "tool_argument_accuracy": 1, "invalid_tool_call_rate": 0, "average_steps": 1.75, "average_latency_ms": 4646.515175001696, "token_usage": 5939, "tool_calls": 3, "expected_calls": 3 }, "cases": [ { "case_id": "arithmetic", "repeat": 0, "agent_run_id": "run_f4baf45c66c34e3f94b60b90f0846a95", "success": true, "tool_calls": 1, "expected_calls": 1, "selected_calls": 1, "accurate_calls": 1, "invalid_calls": 0, "steps": 2, "latency_ms": 4902.329800010193, "token_usage": 1585, "checks": { "completed": true, "tools_selected": true, "tool_arguments": true, "no_extra_calls": true, "tool_results": true, "output": true, "citation": true, "tasks_created": true }, "error_code": null }, { "case_id": "echo", "repeat": 0, "agent_run_id": "run_5cf8341f73fa431ab7978f9ed4fe84c7", "success": true, "tool_calls": 1, "expected_calls": 1, "selected_calls": 1, "accurate_calls": 1, "invalid_calls": 0, "steps": 2, "latency_ms": 5341.693700000178, "token_usage": 1821, "checks": { "completed": true, "tools_selected": true, "tool_arguments": true, "no_extra_calls": true, "tool_results": true, "output": true, "citation": true, "tasks_created": true }, "error_code": null }, { "case_id": "no-tool", "repeat": 0, "agent_run_id": "run_226a20145fbc4737ae2d3e812ff8f25c", "success": true, "tool_calls": 0, "expected_calls": 0, "selected_calls": 0, "accurate_calls": 0, "invalid_calls": 0, "steps": 1, "latency_ms": 1806.5612000063993, "token_usage": 541, "checks": { "completed": true, "tools_selected": true, "tool_arguments": true, "no_extra_calls": true, "tool_results": true, "output": true, "citation": true, "tasks_created": true }, "error_code": null }, { "case_id": "markdown-catalog", "repeat": 0, "agent_run_id": "run_1230c37a1c2c4559b69cbc4e01b4721b", "success": true, "tool_calls": 1, "expected_calls": 1, "selected_calls": 1, "accurate_calls": 1, "invalid_calls": 0, "steps": 2, "latency_ms": 6535.4759999900125, "token_usage": 1992, "checks": { "completed": true, "tools_selected": true, "tool_arguments": true, "no_extra_calls": true, "tool_results": true, "output": true, "citation": true, "tasks_created": true }, "error_code": null } ], "error": null, "error_code": null }