{"record": {"aliases": ["Multi-SWE-Bench"], "artifacts": [{"kind": "repo", "url": "https://github.com/multi-swe-bench/multi-swe-bench/"}], "audits": [], "categories": ["coding_agent"], "description": {"en": "Multilingual SWE-bench variant spanning 7 programming languages; cross-repository context transfer is the measured capability."}, "documents": [{"document_type": "model_card", "id": "model_reports:bytedance_seed2_0_model_card", "model_name": "Seed2.0 (Pro / Lite / Mini)", "organization": "ByteDance", "published": "2026-02-14", "retrieved_at": "2026-09-11", "source": "model_reports", "source_id": "bytedance_seed2_0_model_card", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf", "title": "Seed2.0 (Pro / Lite / Mini)"}], "evidence_summary": {"document_count": 1, "model_count": 2, "model_count_basis": "source_model_id"}, "key": "model-reports:multi_swe_bench", "modality": null, "name": "Multi-SWE-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"registry": "data/model_cards.yml", "score_archive": "data/benchmark_scores.yml", "source_url": "https://github.com/multi-swe-bench/multi-swe-bench/"}, "publisher": null, "released": "2025-04-03", "released_reference": {"basis": "paper_first_version", "note": "First version of the introducing paper: Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving. The source-record description identifies this benchmark or its original partition; no dates or scores are joined by name at runtime.", "source_key": "model-reports:multi_swe_bench", "source_url": "https://arxiv.org/abs/2504.02605"}, "schema_version": 1, "sizes": [], "slug": "multi_swe_bench", "source": "model_reports", "source_benchmark_id": "multi_swe_bench"}, "schema_version": 1, "scores_by_source": {"model_reports": {"rows": [{"benchmark_id": "multi_swe_bench", "comparable_group": "[\"model-reports:multi_swe_bench\",\"multi_swe_bench\",\"as printed in Table 11 (Large Models)\"]", "date_precision": "document_publication", "document_id": "model_reports:bytedance_seed2_0_model_card", "instrument": "multi_swe_bench", "key": "model-reports:multi_swe_bench", "measured_by": "ByteDance", "measurement_kind": "reported_self_score", "model": "Seed2.0 Pro", "model_id": "[\"ByteDance\",\"Seed2.0 Pro\"]", "model_name": "Seed2.0 Pro", "obs_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "observation_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "organization": "ByteDance", "protocol": "as printed in Table 11 (Large Models)", "rank_in_source_response": null, "raw_value": "45.2", "read_from": "pdf_text", "reported_at": "2026-02-14", "reported_by": "self_reported", "reported_date": "2026-02-14", "series_id": "model_reports:multi_swe_bench:default", "source": "model_reports", "source_document_type": "model_card", "source_id": "bytedance_seed2_0_model_card", "source_title": "Seed2.0 (Pro / Lite / Mini)", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf", "value": 45.2, "value_kind": "number"}, {"benchmark_id": "multi_swe_bench", "comparable_group": "[\"model-reports:multi_swe_bench\",\"multi_swe_bench\",\"as printed in Table 12 (Efficient Models)\"]", "date_precision": "document_publication", "document_id": "model_reports:bytedance_seed2_0_model_card", "instrument": "multi_swe_bench", "key": "model-reports:multi_swe_bench", "measured_by": "ByteDance", "measurement_kind": "reported_self_score", "model": "Seed2.0 Lite", "model_id": "[\"ByteDance\",\"Seed2.0 Lite\"]", "model_name": "Seed2.0 Lite", "obs_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 12 (Efficient Models)\u0000Seed2.0 Lite", "observation_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 12 (Efficient Models)\u0000Seed2.0 Lite", "organization": "ByteDance", "protocol": "as printed in Table 12 (Efficient Models)", "rank_in_source_response": null, "raw_value": "41.1", "read_from": "pdf_text", "reported_at": "2026-02-14", "reported_by": "self_reported", "reported_date": "2026-02-14", "series_id": "model_reports:multi_swe_bench:default", "source": "model_reports", "source_document_type": "model_card", "source_id": "bytedance_seed2_0_model_card", "source_title": "Seed2.0 (Pro / Lite / Mini)", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf", "value": 41.1, "value_kind": "number"}], "series": {"declared_max": null, "direction": "higher_is_better", "direction_basis": "reported_metric", "display_scale": null, "first_score_record": {"date_precision": "document_publication", "obs_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "reported_at": "2026-02-14", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf"}, "first_score_report": {"date_precision": "document_publication", "obs_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "reported_at": "2026-02-14", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf"}, "key": "model-reports:multi_swe_bench", "max_score_contradicted": false, "metric": "resolved", "observation_count": 2, "observed_max": 45.2, "score_summary": {"display_max": 45.2, "display_multiplier": 1, "model_count": 2, "model_count_basis": "source_model_id", "numeric_count": 2, "raw_max": 45.2, "raw_min": 41.1, "source_reference": {"obs_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "observation_id": "curated\u0000multi_swe_bench\u0000bytedance_seed2_0_model_card\u0000multi_swe_bench\u0000as printed in Table 11 (Large Models)\u0000Seed2.0 Pro", "reported_at": "2026-02-14", "reported_date": "2026-02-14", "source_id": "bytedance_seed2_0_model_card", "source_url": "https://lf3-static.bytednsdoc.com/obj/eden-cn/lapzild-tss/ljhwZthlaukjlkulzlp/seed2/0214/Seed2.0%20Model%20Card.pdf"}, "unit": "percent"}, "series_id": "model_reports:multi_swe_bench:default", "unit": "percent"}}}, "siblings": []}
