data/extracted/swt-bench.jsonl

{"agent_name": "1.0.2", "llm_base": "claude-3-5-sonnet-20241022", "openness": "closed_api_available", "tool_usage": "standard", "score": 65.4, "metric": "success_rate", "submission_time": "2025-11-24T23:38:02.231319", "tags": ["swt-bench"], "total_cost": 42.7, "total_runtime": 627.0}
{"agent_name": "1.0.1", "llm_base": "gpt-4o-2024-11-20", "openness": "closed_api_available", "tool_usage": "standard", "score": 62.3, "metric": "success_rate", "submission_time": "2025-11-24T23:38:02.231344", "tags": ["swt-bench"], "total_cost": 41.15, "total_runtime": 611.5}
{"agent_name": "1.0.0", "llm_base": "gpt-4-turbo-2024-04-09", "openness": "closed_api_available", "tool_usage": "standard", "score": 54.1, "metric": "success_rate", "submission_time": "2025-11-24T23:38:02.231356", "tags": ["swt-bench"], "total_cost": 37.05, "total_runtime": 570.5}
{"agent_name": "0.9.5", "llm_base": "gpt-4o-mini-2024-07-18", "openness": "closed_api_available", "tool_usage": "standard", "score": 47.8, "metric": "success_rate", "submission_time": "2025-11-24T23:38:02.231365", "tags": ["swt-bench"], "total_cost": 33.9, "total_runtime": 539.0}
{"agent_name": "0.9.0", "llm_base": "claude-3-opus-20240229", "openness": "closed_api_available", "tool_usage": "custom_interface", "score": 44.2, "metric": "success_rate", "submission_time": "2025-11-24T23:38:02.231373", "tags": ["swt-bench"], "total_cost": 32.1, "total_runtime": 521.0}