{"record": {"aliases": ["SlopCodeBench"], "artifacts": [{"kind": "website", "url": "https://www.scbench.ai"}], "audits": [{"audit_date": "2026-08-09", "audit_url": "https://june.kim/auditing-slopcodebench", "auditor": "June Kim", "finding": "June Kim's audit reports that the erosion metric measures static code-shape drift, not yet extension robustness: its correlation with passing the next checkpoint is −0.018, weaker than raw line count at −0.212, and iteration is confounded because every checkpoint adds requirements. In his 12-problem sample, 28 of 343 core tests assert exact values no visible spec determines, and of all 196 answer keys run through the benchmark's own harness, 4 are deterministically defective and 1 is unstable.", "receipts": ["https://github.com/kimjune01/slopcodebench-audit"]}], "categories": ["coding"], "description": {"en": "36 problems run as checkpoint sequences (196 checkpoints in v1.0): the agent extends its own earlier solution as new requirements arrive, so a checkpoint score reflects the accumulated codebase rather than a fresh attempt, and the headline erosion measures (verbosity, dead branches, redundant structure) are not a plain solve rate."}, "documents": [{"document_type": "benchmark_leaderboard", "id": "model_reports:slopcodebench_leaderboard_2026_04_24", "model_name": null, "organization": "SprocketLab", "published": "2026-04-24", "retrieved_at": "2026-11-04", "source": "model_reports", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_url": "https://www.scbench.ai/leaderboard", "title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)"}], "evidence_summary": {"document_count": 1, "model_count": 15, "model_count_basis": "source_model_id"}, "key": "model-reports:slopcodebench", "modality": null, "name": "SlopCodeBench", "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://www.scbench.ai"}, "publisher": null, "released": null, "released_reference": null, "schema_version": 1, "sizes": [], "slug": "slopcodebench", "source": "model_reports", "source_benchmark_id": "slopcodebench"}, "schema_version": 1, "scores_by_source": {"model_reports": {"rows": [{"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GLM 5.1", "model_id": "[\"Zhipu AI\",\"GLM 5.1\"]", "model_name": "GLM 5.1", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000GLM 5.1", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000GLM 5.1", "organization": "Zhipu AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "13.78", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 13.78, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Kimi K2.5", "model_id": "[\"Moonshot AI\",\"Kimi K2.5\"]", "model_name": "Kimi K2.5", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Kimi K2.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Kimi K2.5", "organization": "Moonshot AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "7.14", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 7.14, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "MiniMax M2.7", "model_id": "[\"MiniMax\",\"MiniMax M2.7\"]", "model_name": "MiniMax M2.7", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000MiniMax M2.7", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000MiniMax M2.7", "organization": "MiniMax", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "4.08", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 4.08, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Opus 4.5", "model_id": "[\"Anthropic\",\"Opus 4.5\"]", "model_name": "Opus 4.5", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.5", "organization": "Anthropic", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "17.35", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 17.35, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Opus 4.6", "model_id": "[\"Anthropic\",\"Opus 4.6\"]", "model_name": "Opus 4.6", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.6", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.6", "organization": "Anthropic", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "20.92", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 20.92, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Opus 4.7", "model_id": "[\"Anthropic\",\"Opus 4.7\"]", "model_name": "Opus 4.7", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.7", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Opus 4.7", "organization": "Anthropic", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "20.92", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 20.92, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Sonnet 4.6", "model_id": "[\"Anthropic\",\"Sonnet 4.6\"]", "model_name": "Sonnet 4.6", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Sonnet 4.6", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000Sonnet 4.6", "organization": "Anthropic", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high", "rank_in_source_response": null, "raw_value": "16.84", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 16.84, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.2-Codex", "model_id": "[\"OpenAI\",\"GPT 5.2-Codex\"]", "model_name": "GPT 5.2-Codex", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.2-Codex", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.2-Codex", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "21.94", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 21.94, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.3-Codex", "model_id": "[\"OpenAI\",\"GPT 5.3-Codex\"]", "model_name": "GPT 5.3-Codex", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.3-Codex", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.3-Codex", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "26.02", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 26.02, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.3-Codex-Spark", "model_id": "[\"OpenAI\",\"GPT 5.3-Codex-Spark\"]", "model_name": "GPT 5.3-Codex-Spark", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.3-Codex-Spark", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.3-Codex-Spark", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "8.16", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 8.16, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.4", "model_id": "[\"OpenAI\",\"GPT 5.4\"]", "model_name": "GPT 5.4", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.4", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.4", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "23.47", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 23.47, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.4-Mini", "model_id": "[\"OpenAI\",\"GPT 5.4-Mini\"]", "model_name": "GPT 5.4-Mini", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.4-Mini", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.4-Mini", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "13.78", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 13.78, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GPT 5.5", "model_id": "[\"OpenAI\",\"GPT 5.5\"]", "model_name": "GPT 5.5", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.5", "organization": "OpenAI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high", "rank_in_source_response": null, "raw_value": "28.06", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 28.06, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Cursor CLI\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Composer 2", "model_id": "[\"Cursor\",\"Composer 2\"]", "model_name": "Composer 2", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Cursor CLI\u0000Composer 2", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Cursor CLI\u0000Composer 2", "organization": "Cursor", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Cursor CLI", "rank_in_source_response": null, "raw_value": "16.33", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 16.33, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Kimi K2.5", "model_id": "[\"Moonshot AI\",\"Kimi K2.5\"]", "model_name": "Kimi K2.5", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\u0000Kimi K2.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\u0000Kimi K2.5", "organization": "Moonshot AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high", "rank_in_source_response": null, "raw_value": "9.69", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 9.69, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Kimi K2.6", "model_id": "[\"Moonshot AI\",\"Kimi K2.6\"]", "model_name": "Kimi K2.6", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\u0000Kimi K2.6", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high\u0000Kimi K2.6", "organization": "Moonshot AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: Kimi CLI; thinking: high", "rank_in_source_response": null, "raw_value": "18.88", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 18.88, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "Kimi K2.5", "model_id": "[\"Moonshot AI\",\"Kimi K2.5\"]", "model_name": "Kimi K2.5", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\u0000Kimi K2.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\u0000Kimi K2.5", "organization": "Moonshot AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode", "rank_in_source_response": null, "raw_value": "8.67", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 8.67, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "MiniMax M2.7", "model_id": "[\"MiniMax\",\"MiniMax M2.7\"]", "model_name": "MiniMax M2.7", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\u0000MiniMax M2.7", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode\u0000MiniMax M2.7", "organization": "MiniMax", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode", "rank_in_source_response": null, "raw_value": "3.57", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 3.57, "value_kind": "number"}, {"benchmark_id": "slopcodebench", "comparable_group": "[\"model-reports:slopcodebench\",\"slopcodebench_v1_0\",\"36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode; thinking: high\"]", "date_precision": "document_publication", "document_id": "model_reports:slopcodebench_leaderboard_2026_04_24", "instrument": "slopcodebench_v1_0", "key": "model-reports:slopcodebench", "measured_by": "SprocketLab", "measurement_kind": "benchmark_publisher_run", "model": "GLM 5.1", "model_id": "[\"Zhipu AI\",\"GLM 5.1\"]", "model_name": "GLM 5.1", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode; thinking: high\u0000GLM 5.1", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode; thinking: high\u0000GLM 5.1", "organization": "Zhipu AI", "protocol": "36 problems, 196 checkpoints; isolated solve rate; agent harness: OpenCode; thinking: high", "rank_in_source_response": null, "raw_value": "8.16", "read_from": "html_text", "reported_at": "2026-04-24", "reported_by": "third_party", "reported_date": "2026-04-24", "series_id": "model_reports:slopcodebench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_title": "SlopCodeBench leaderboard (v1.0, best version by % checkpoints view)", "source_url": "https://www.scbench.ai/leaderboard", "value": 8.16, "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\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000GLM 5.1", "reported_at": "2026-04-24", "source_url": "https://www.scbench.ai/leaderboard"}, "first_score_report": {"date_precision": "document_publication", "obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Claude Code; thinking: high\u0000GLM 5.1", "reported_at": "2026-04-24", "source_url": "https://www.scbench.ai/leaderboard"}, "key": "model-reports:slopcodebench", "max_score_contradicted": false, "metric": "isolated_solve", "observation_count": 19, "observed_max": 28.06, "score_summary": {"display_max": 28.06, "display_multiplier": 1, "model_count": 15, "model_count_basis": "source_model_id", "numeric_count": 19, "raw_max": 28.06, "raw_min": 3.57, "source_reference": {"obs_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.5", "observation_id": "curated\u0000slopcodebench\u0000slopcodebench_leaderboard_2026_04_24\u0000slopcodebench_v1_0\u000036 problems, 196 checkpoints; isolated solve rate; agent harness: Codex; thinking: high\u0000GPT 5.5", "reported_at": "2026-04-24", "reported_date": "2026-04-24", "source_id": "slopcodebench_leaderboard_2026_04_24", "source_url": "https://www.scbench.ai/leaderboard"}, "unit": "percent"}, "series_id": "model_reports:slopcodebench:default", "unit": "percent"}}}, "siblings": []}