data/extracted/swe-bench-multimodal.jsonl

{"agent_name": "1.0.2", "llm_base": "claude-3-5-sonnet-20241022", "openness": "closed_api_available", "tool_usage": "standard", "score": 42.1, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.231057", "tags": ["swe-bench-multimodal"], "total_cost": 31.05, "total_runtime": 510.5}
{"agent_name": "1.0.1", "llm_base": "gpt-4o-2024-11-20", "openness": "closed_api_available", "tool_usage": "standard", "score": 39.5, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.231073", "tags": ["swe-bench-multimodal"], "total_cost": 29.75, "total_runtime": 497.5}
{"agent_name": "1.0.0", "llm_base": "gpt-4-turbo-2024-04-09", "openness": "closed_api_available", "tool_usage": "standard", "score": 34.2, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.231082", "tags": ["swe-bench-multimodal"], "total_cost": 27.1, "total_runtime": 471.0}
{"agent_name": "0.9.5", "llm_base": "gpt-4o-mini-2024-07-18", "openness": "closed_api_available", "tool_usage": "standard", "score": 28.9, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.231088", "tags": ["swe-bench-multimodal"], "total_cost": 24.45, "total_runtime": 444.5}
{"agent_name": "0.9.0", "llm_base": "claude-3-opus-20240229", "openness": "closed_api_available", "tool_usage": "custom_interface", "score": 25.7, "metric": "resolve_rate", "submission_time": "2025-11-24T23:38:02.231093", "tags": ["swe-bench-multimodal"], "total_cost": 22.85, "total_runtime": 428.5}