data/extracted/swe-bench.jsonl

{"agent_name": "1.0.2", "llm_base": "claude-3-5-sonnet-20241022", "openness": "closed_api_available", "tool_usage": "standard", "score": 48.3, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.230638", "tags": ["swe-bench"], "total_cost": 34.15, "total_runtime": 541.5}
{"agent_name": "1.0.1", "llm_base": "gpt-4o-2024-11-20", "openness": "closed_api_available", "tool_usage": "standard", "score": 45.1, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.230668", "tags": ["swe-bench"], "total_cost": 32.55, "total_runtime": 525.5}
{"agent_name": "1.0.0", "llm_base": "gpt-4-turbo-2024-04-09", "openness": "closed_api_available", "tool_usage": "standard", "score": 38.7, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.230681", "tags": ["swe-bench"], "total_cost": 29.35, "total_runtime": 493.5}
{"agent_name": "0.9.5", "llm_base": "gpt-4o-mini-2024-07-18", "openness": "closed_api_available", "tool_usage": "standard", "score": 32.5, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.230689", "tags": ["swe-bench"], "total_cost": 26.25, "total_runtime": 462.5}
{"agent_name": "0.9.0", "llm_base": "claude-3-opus-20240229", "openness": "closed_api_available", "tool_usage": "custom_interface", "score": 29.8, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.230696", "tags": ["swe-bench"], "total_cost": 24.9, "total_runtime": 449.0}