{ "schema_version": "0.2.2", "evaluation_id": "swebench_lite_dev/RedHatAI/Kimi-K2.6-NVFP4/1784247001.8595154", "retrieved_timestamp": "1784247001.8595154", "source_metadata": { "source_name": "SWE-bench harness", "source_type": "evaluation_run", "source_organization_name": "RedHatAI", "evaluator_relationship": "first_party", "additional_details": { "note": "predictions generated with mini-swe-agent, resolved-rate scored with the official SWE-bench harness (swebench.harness.run_evaluation)" } }, "eval_library": { "name": "swebench", "version": "4.1.0" }, "model_info": { "name": "RedHatAI/Kimi-K2.6-NVFP4", "id": "RedHatAI/Kimi-K2.6-NVFP4", "developer": "RedHatAI", "inference_engine": { "name": "vllm", "version": "0.24.0" }, "additional_details": { "profile": "kimi_nvfp4", "subset": "lite", "split": "dev" } }, "evaluation_results": [ { "evaluation_name": "swebench_lite_dev/resolved_rate", "source_data": { "dataset_name": "SWE-bench Lite dev", "source_type": "hf_dataset", "hf_repo": "princeton-nlp/SWE-Bench_Lite", "hf_split": "dev", "samples_number": 23 }, "metric_config": { "evaluation_description": "Resolve rate: fraction of benchmark instances where the submitted patch passes verification (0.0-1.0), scored with the official SWE-bench harness.", "lower_is_better": false, "score_type": "continuous", "min_score": 0.0, "max_score": 1.0 }, "score_details": { "score": 0.21739130434782608, "details": { "total_instances": "23", "resolved_instances": "5", "submitted_instances": "23", "completed_instances": "19", "unresolved_instances": "14", "empty_patch_instances": "4", "error_instances": "0" }, "completed_ids": [ "marshmallow-code__marshmallow-1343", "marshmallow-code__marshmallow-1359", "pvlib__pvlib-python-1072", "pvlib__pvlib-python-1154", "pvlib__pvlib-python-1606", "pvlib__pvlib-python-1707", "pvlib__pvlib-python-1854", "pydicom__pydicom-1139", "pydicom__pydicom-1256", "pydicom__pydicom-1413", "pydicom__pydicom-1694", "pydicom__pydicom-901", "pylint-dev__astroid-1196", "pylint-dev__astroid-1268", "pylint-dev__astroid-1866", "pylint-dev__astroid-1978", "pyvista__pyvista-4315", "sqlfluff__sqlfluff-1517", "sqlfluff__sqlfluff-2419" ], "submitted_ids": [ "marshmallow-code__marshmallow-1343", "marshmallow-code__marshmallow-1359", "pvlib__pvlib-python-1072", "pvlib__pvlib-python-1154", "pvlib__pvlib-python-1606", "pvlib__pvlib-python-1707", "pvlib__pvlib-python-1854", "pydicom__pydicom-1139", "pydicom__pydicom-1256", "pydicom__pydicom-1413", "pydicom__pydicom-1694", "pydicom__pydicom-901", "pylint-dev__astroid-1196", "pylint-dev__astroid-1268", "pylint-dev__astroid-1333", "pylint-dev__astroid-1866", "pylint-dev__astroid-1978", "pyvista__pyvista-4315", "sqlfluff__sqlfluff-1517", "sqlfluff__sqlfluff-1625", "sqlfluff__sqlfluff-1733", "sqlfluff__sqlfluff-1763", "sqlfluff__sqlfluff-2419" ], "resolved_ids": [ "marshmallow-code__marshmallow-1343", "pydicom__pydicom-1256", "pydicom__pydicom-1694", "pylint-dev__astroid-1268", "sqlfluff__sqlfluff-2419" ] }, "generation_config": { "generation_args": { "agentic_eval_config": { "available_tools": [ { "name": "bash" } ] }, "max_attempts": 1 } } }, { "evaluation_name": "swebench_lite_dev/submission_rate", "source_data": { "dataset_name": "SWE-bench Lite dev", "source_type": "hf_dataset", "hf_repo": "princeton-nlp/SWE-Bench_Lite", "hf_split": "dev", "samples_number": 23 }, "metric_config": { "evaluation_description": "Submission rate (Submitted / total instances).", "lower_is_better": false, "score_type": "continuous", "min_score": 0.0, "max_score": 1.0 }, "score_details": { "score": 1.0, "details": { "total_instances": "23", "submitted_instances": "23", "unsubmitted_instances": "0" }, "submitted_ids": [ "marshmallow-code__marshmallow-1343", "marshmallow-code__marshmallow-1359", "pvlib__pvlib-python-1072", "pvlib__pvlib-python-1154", "pvlib__pvlib-python-1606", "pvlib__pvlib-python-1707", "pvlib__pvlib-python-1854", "pydicom__pydicom-1139", "pydicom__pydicom-1256", "pydicom__pydicom-1413", "pydicom__pydicom-1694", "pydicom__pydicom-901", "pylint-dev__astroid-1196", "pylint-dev__astroid-1268", "pylint-dev__astroid-1333", "pylint-dev__astroid-1866", "pylint-dev__astroid-1978", "pyvista__pyvista-4315", "sqlfluff__sqlfluff-1517", "sqlfluff__sqlfluff-1625", "sqlfluff__sqlfluff-1733", "sqlfluff__sqlfluff-1763", "sqlfluff__sqlfluff-2419" ] }, "generation_config": { "generation_args": { "agentic_eval_config": { "available_tools": [ { "name": "bash" } ] }, "max_attempts": 1 } } } ] }