{"record": {"aliases": ["YapBench", "Do Chatbot LLMs Talk Too Much? The YapBench Benchmark"], "artifacts": [{"kind": "paper", "url": "https://arxiv.org/abs/2601.00624"}], "audits": [], "categories": ["general"], "description": {"en": "Lower is better. YapScore counts characters a response adds beyond a curated minimal-sufficient answer, and YapIndex is the equal-weight mean of the three category medians (arXiv:2601.00624). It measures verbosity on brevity-ideal prompts, not correctness: a shorter answer can be a worse one. The paper evaluates 76 configurations on version 0.1, and the live leaderboard updates separately, so prompt-set version and reasoning mode change the number."}, "documents": [{"document_type": "benchmark_leaderboard", "id": "model_reports:yapbench_v0_1_paper_leaderboard", "model_name": null, "organization": "YapBench authors", "published": "2026-01-02", "retrieved_at": "2026-11-15", "source": "model_reports", "source_id": "yapbench_v0_1_paper_leaderboard", "source_url": "https://arxiv.org/abs/2601.00624", "title": "YapBench v0.1 full leaderboard (Table 6)"}], "evidence_summary": {"document_count": 1, "model_count": 76, "model_count_basis": "source_model_id"}, "key": "model-reports:yapbench", "modality": null, "name": "YapBench", "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://arxiv.org/abs/2601.00624"}, "publisher": null, "released": "2026-01-02", "released_reference": {"basis": "benchmark_release", "source_key": "model-reports:yapbench", "source_url": "https://arxiv.org/abs/2601.00624"}, "schema_version": 1, "sizes": [], "slug": "yapbench", "source": "model_reports", "source_benchmark_id": "yapbench"}, "schema_version": 1, "scores_by_source": {"model_reports": {"rows": [{"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-haiku-4.5 (reasoning)", "model_id": "[\"Anthropic\",\"claude-haiku-4.5 (reasoning)\"]", "model_name": "claude-haiku-4.5 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-haiku-4.5 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-haiku-4.5 (reasoning)", "organization": "Anthropic", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "335.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 335.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-opus-4.5 (reasoning)", "model_id": "[\"Anthropic\",\"claude-opus-4.5 (reasoning)\"]", "model_name": "claude-opus-4.5 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-opus-4.5 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-opus-4.5 (reasoning)", "organization": "Anthropic", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "99.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 99.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-sonnet-4.5 (reasoning)", "model_id": "[\"Anthropic\",\"claude-sonnet-4.5 (reasoning)\"]", "model_name": "claude-sonnet-4.5 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-sonnet-4.5 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-sonnet-4.5 (reasoning)", "organization": "Anthropic", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "278.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 278.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "deepseek-v3.2 (reasoning)", "model_id": "[\"DeepSeek\",\"deepseek-v3.2 (reasoning)\"]", "model_name": "deepseek-v3.2 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000deepseek-v3.2 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000deepseek-v3.2 (reasoning)", "organization": "DeepSeek", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "215.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 215.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.5-flash (reasoning)", "model_id": "[\"Google\",\"gemini-2.5-flash (reasoning)\"]", "model_name": "gemini-2.5-flash (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-2.5-flash (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-2.5-flash (reasoning)", "organization": "Google", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "195.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 195.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.5-flash-lite (reasoning)", "model_id": "[\"Google\",\"gemini-2.5-flash-lite (reasoning)\"]", "model_name": "gemini-2.5-flash-lite (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-2.5-flash-lite (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-2.5-flash-lite (reasoning)", "organization": "Google", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "280.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 280.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-3-flash-preview (reasoning)", "model_id": "[\"Google\",\"gemini-3-flash-preview (reasoning)\"]", "model_name": "gemini-3-flash-preview (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-3-flash-preview (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gemini-3-flash-preview (reasoning)", "organization": "Google", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "340.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 340.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5.1 (reasoning)", "model_id": "[\"OpenAI\",\"gpt-5.1 (reasoning)\"]", "model_name": "gpt-5.1 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gpt-5.1 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gpt-5.1 (reasoning)", "organization": "OpenAI", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "120.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 120.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5.2 (reasoning)", "model_id": "[\"OpenAI\",\"gpt-5.2 (reasoning)\"]", "model_name": "gpt-5.2 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gpt-5.2 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000gpt-5.2 (reasoning)", "organization": "OpenAI", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "89.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 89.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "nova-2-lite-v1 (reasoning)", "model_id": "[\"Amazon\",\"nova-2-lite-v1 (reasoning)\"]", "model_name": "nova-2-lite-v1 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000nova-2-lite-v1 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000nova-2-lite-v1 (reasoning)", "organization": "Amazon", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "788.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 788.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "phi-4-reasoning-plus (reasoning)", "model_id": "[\"Microsoft\",\"phi-4-reasoning-plus (reasoning)\"]", "model_name": "phi-4-reasoning-plus (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000phi-4-reasoning-plus (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000phi-4-reasoning-plus (reasoning)", "organization": "Microsoft", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "281.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 281.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen-plus (reasoning)", "model_id": "[\"Qwen\",\"qwen-plus (reasoning)\"]", "model_name": "qwen-plus (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen-plus (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen-plus (reasoning)", "organization": "Qwen", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "800.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 800.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-235b-a22b-2507 (reasoning)", "model_id": "[\"Qwen\",\"qwen3-235b-a22b-2507 (reasoning)\"]", "model_name": "qwen3-235b-a22b-2507 (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen3-235b-a22b-2507 (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen3-235b-a22b-2507 (reasoning)", "organization": "Qwen", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "260.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 260.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"reasoning mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-coder (reasoning)", "model_id": "[\"Qwen\",\"qwen3-coder (reasoning)\"]", "model_name": "qwen3-coder (reasoning)", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen3-coder (reasoning)", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000qwen3-coder (reasoning)", "organization": "Qwen", "protocol": "reasoning mode", "rank_in_source_response": null, "raw_value": "325.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 325.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-3.5-haiku", "model_id": "[\"Anthropic\",\"claude-3.5-haiku\"]", "model_name": "claude-3.5-haiku", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-3.5-haiku", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-3.5-haiku", "organization": "Anthropic", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "401.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 401.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-3.5-sonnet", "model_id": "[\"Anthropic\",\"claude-3.5-sonnet\"]", "model_name": "claude-3.5-sonnet", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-3.5-sonnet", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-3.5-sonnet", "organization": "Anthropic", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "199.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 199.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-haiku-4.5", "model_id": "[\"Anthropic\",\"claude-haiku-4.5\"]", "model_name": "claude-haiku-4.5", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-haiku-4.5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-haiku-4.5", "organization": "Anthropic", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "333.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 333.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-opus-4.5", "model_id": "[\"Anthropic\",\"claude-opus-4.5\"]", "model_name": "claude-opus-4.5", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-opus-4.5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-opus-4.5", "organization": "Anthropic", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "97.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 97.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "claude-sonnet-4.5", "model_id": "[\"Anthropic\",\"claude-sonnet-4.5\"]", "model_name": "claude-sonnet-4.5", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-sonnet-4.5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000claude-sonnet-4.5", "organization": "Anthropic", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "285.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 285.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "deepseek-chat", "model_id": "[\"DeepSeek\",\"deepseek-chat\"]", "model_name": "deepseek-chat", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000deepseek-chat", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000deepseek-chat", "organization": "DeepSeek", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "345.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 345.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "deepseek-v3.2", "model_id": "[\"DeepSeek\",\"deepseek-v3.2\"]", "model_name": "deepseek-v3.2", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000deepseek-v3.2", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000deepseek-v3.2", "organization": "DeepSeek", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "426.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 426.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "devstral-2512", "model_id": "[\"Mistral\",\"devstral-2512\"]", "model_name": "devstral-2512", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000devstral-2512", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000devstral-2512", "organization": "Mistral", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "449.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 449.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.0-flash-001", "model_id": "[\"Google\",\"gemini-2.0-flash-001\"]", "model_name": "gemini-2.0-flash-001", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.0-flash-001", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.0-flash-001", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "326.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 326.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.0-flash-lite-001", "model_id": "[\"Google\",\"gemini-2.0-flash-lite-001\"]", "model_name": "gemini-2.0-flash-lite-001", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.0-flash-lite-001", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.0-flash-lite-001", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "227.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 227.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.5-flash", "model_id": "[\"Google\",\"gemini-2.5-flash\"]", "model_name": "gemini-2.5-flash", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-flash", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-flash", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "210.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 210.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.5-flash-lite", "model_id": "[\"Google\",\"gemini-2.5-flash-lite\"]", "model_name": "gemini-2.5-flash-lite", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-flash-lite", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-flash-lite", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "476.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 476.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-2.5-pro", "model_id": "[\"Google\",\"gemini-2.5-pro\"]", "model_name": "gemini-2.5-pro", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-pro", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-2.5-pro", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "539.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 539.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-3-flash-preview", "model_id": "[\"Google\",\"gemini-3-flash-preview\"]", "model_name": "gemini-3-flash-preview", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-3-flash-preview", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-3-flash-preview", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "339.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 339.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gemini-3-pro-preview", "model_id": "[\"Google\",\"gemini-3-pro-preview\"]", "model_name": "gemini-3-pro-preview", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-3-pro-preview", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gemini-3-pro-preview", "organization": "Google", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "226.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 226.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "glm-4.5", "model_id": "[\"Z.ai\",\"glm-4.5\"]", "model_name": "glm-4.5", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.5", "organization": "Z.ai", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "1427.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 1427.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "glm-4.6:exacto", "model_id": "[\"Z.ai\",\"glm-4.6:exacto\"]", "model_name": "glm-4.6:exacto", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.6:exacto", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.6:exacto", "organization": "Z.ai", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "930.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 930.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "glm-4.6v", "model_id": "[\"Z.ai\",\"glm-4.6v\"]", "model_name": "glm-4.6v", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.6v", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.6v", "organization": "Z.ai", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "410.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 410.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "glm-4.7", "model_id": "[\"Z.ai\",\"glm-4.7\"]", "model_name": "glm-4.7", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.7", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.7", "organization": "Z.ai", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "66.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 66.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-3.5-turbo", "model_id": "[\"OpenAI\",\"gpt-3.5-turbo\"]", "model_name": "gpt-3.5-turbo", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-3.5-turbo", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-3.5-turbo", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "22.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 22.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4", "model_id": "[\"OpenAI\",\"gpt-4\"]", "model_name": "gpt-4", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "51.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 51.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4-turbo", "model_id": "[\"OpenAI\",\"gpt-4-turbo\"]", "model_name": "gpt-4-turbo", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4-turbo", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4-turbo", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "252.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 252.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4.1", "model_id": "[\"OpenAI\",\"gpt-4.1\"]", "model_name": "gpt-4.1", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "168.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 168.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4.1-mini", "model_id": "[\"OpenAI\",\"gpt-4.1-mini\"]", "model_name": "gpt-4.1-mini", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1-mini", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1-mini", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "75.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 75.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4.1-nano", "model_id": "[\"OpenAI\",\"gpt-4.1-nano\"]", "model_name": "gpt-4.1-nano", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1-nano", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4.1-nano", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "105.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 105.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4o", "model_id": "[\"OpenAI\",\"gpt-4o\"]", "model_name": "gpt-4o", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4o", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4o", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "167.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 167.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-4o-mini", "model_id": "[\"OpenAI\",\"gpt-4o-mini\"]", "model_name": "gpt-4o-mini", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4o-mini", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-4o-mini", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "183.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 183.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5", "model_id": "[\"OpenAI\",\"gpt-5\"]", "model_name": "gpt-5", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "100.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 100.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5-mini", "model_id": "[\"OpenAI\",\"gpt-5-mini\"]", "model_name": "gpt-5-mini", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5-mini", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5-mini", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "250.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 250.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5-nano", "model_id": "[\"OpenAI\",\"gpt-5-nano\"]", "model_name": "gpt-5-nano", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5-nano", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5-nano", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "175.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 175.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5.1", "model_id": "[\"OpenAI\",\"gpt-5.1\"]", "model_name": "gpt-5.1", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.1", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.1", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "111.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 111.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5.1-codex", "model_id": "[\"OpenAI\",\"gpt-5.1-codex\"]", "model_name": "gpt-5.1-codex", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.1-codex", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.1-codex", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "85.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 85.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-5.2", "model_id": "[\"OpenAI\",\"gpt-5.2\"]", "model_name": "gpt-5.2", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.2", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-5.2", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "86.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 86.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-oss-120b", "model_id": "[\"OpenAI\",\"gpt-oss-120b\"]", "model_name": "gpt-oss-120b", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-oss-120b", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-oss-120b", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "269.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 269.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "gpt-oss-20b", "model_id": "[\"OpenAI\",\"gpt-oss-20b\"]", "model_name": "gpt-oss-20b", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-oss-20b", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000gpt-oss-20b", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "199.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 199.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "grok-4", "model_id": "[\"xAI\",\"grok-4\"]", "model_name": "grok-4", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4", "organization": "xAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "126.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 126.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "grok-4-fast", "model_id": "[\"xAI\",\"grok-4-fast\"]", "model_name": "grok-4-fast", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4-fast", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4-fast", "organization": "xAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "70.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 70.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "grok-4.1-fast", "model_id": "[\"xAI\",\"grok-4.1-fast\"]", "model_name": "grok-4.1-fast", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4.1-fast", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-4.1-fast", "organization": "xAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "98.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 98.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "grok-code-fast-1", "model_id": "[\"xAI\",\"grok-code-fast-1\"]", "model_name": "grok-code-fast-1", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-code-fast-1", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000grok-code-fast-1", "organization": "xAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "284.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 284.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "kimi-k2-0905", "model_id": "[\"Moonshot AI\",\"kimi-k2-0905\"]", "model_name": "kimi-k2-0905", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000kimi-k2-0905", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000kimi-k2-0905", "organization": "Moonshot AI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "44.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 44.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "llama-3.1-8b-instruct", "model_id": "[\"Meta\",\"llama-3.1-8b-instruct\"]", "model_name": "llama-3.1-8b-instruct", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-3.1-8b-instruct", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-3.1-8b-instruct", "organization": "Meta", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "315.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 315.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "llama-3.3-70b-instruct", "model_id": "[\"Meta\",\"llama-3.3-70b-instruct\"]", "model_name": "llama-3.3-70b-instruct", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-3.3-70b-instruct", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-3.3-70b-instruct", "organization": "Meta", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "312.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 312.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "llama-4-maverick", "model_id": "[\"Meta\",\"llama-4-maverick\"]", "model_name": "llama-4-maverick", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-4-maverick", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-4-maverick", "organization": "Meta", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "342.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 342.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "llama-4-scout", "model_id": "[\"Meta\",\"llama-4-scout\"]", "model_name": "llama-4-scout", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-4-scout", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000llama-4-scout", "organization": "Meta", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "350.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 350.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "minimax-m2", "model_id": "[\"MiniMax\",\"minimax-m2\"]", "model_name": "minimax-m2", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000minimax-m2", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000minimax-m2", "organization": "MiniMax", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "297.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 297.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "mistral-large-2512", "model_id": "[\"Mistral\",\"mistral-large-2512\"]", "model_name": "mistral-large-2512", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-large-2512", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-large-2512", "organization": "Mistral", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "444.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 444.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "mistral-medium-3", "model_id": "[\"Mistral\",\"mistral-medium-3\"]", "model_name": "mistral-medium-3", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-medium-3", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-medium-3", "organization": "Mistral", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "361.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 361.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "mistral-small-3.1-24b-instruct", "model_id": "[\"Mistral\",\"mistral-small-3.1-24b-instruct\"]", "model_name": "mistral-small-3.1-24b-instruct", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-small-3.1-24b-instruct", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000mistral-small-3.1-24b-instruct", "organization": "Mistral", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "389.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 389.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "nova-2-lite-v1", "model_id": "[\"Amazon\",\"nova-2-lite-v1\"]", "model_name": "nova-2-lite-v1", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000nova-2-lite-v1", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000nova-2-lite-v1", "organization": "Amazon", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "896.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 896.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "o3", "model_id": "[\"OpenAI\",\"o3\"]", "model_name": "o3", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o3", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o3", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "84.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 84.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "o3-mini", "model_id": "[\"OpenAI\",\"o3-mini\"]", "model_name": "o3-mini", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o3-mini", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o3-mini", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "153.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 153.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "o4-mini", "model_id": "[\"OpenAI\",\"o4-mini\"]", "model_name": "o4-mini", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o4-mini", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000o4-mini", "organization": "OpenAI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "115.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 115.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "olmo-2-0325-32b-instruct", "model_id": "[\"Allen Institute for AI\",\"olmo-2-0325-32b-instruct\"]", "model_name": "olmo-2-0325-32b-instruct", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000olmo-2-0325-32b-instruct", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000olmo-2-0325-32b-instruct", "organization": "Allen Institute for AI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "268.7", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 268.7, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "olmo-3.1-32b-think:free", "model_id": "[\"Allen Institute for AI\",\"olmo-3.1-32b-think:free\"]", "model_name": "olmo-3.1-32b-think:free", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000olmo-3.1-32b-think:free", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000olmo-3.1-32b-think:free", "organization": "Allen Institute for AI", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "530.5", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 530.5, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "phi-4-reasoning-plus", "model_id": "[\"Microsoft\",\"phi-4-reasoning-plus\"]", "model_name": "phi-4-reasoning-plus", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000phi-4-reasoning-plus", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000phi-4-reasoning-plus", "organization": "Microsoft", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "281.2", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 281.2, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen-plus", "model_id": "[\"Qwen\",\"qwen-plus\"]", "model_name": "qwen-plus", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen-plus", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen-plus", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "267.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 267.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-14b", "model_id": "[\"Qwen\",\"qwen3-14b\"]", "model_name": "qwen3-14b", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-14b", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-14b", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "558.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 558.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-235b-a22b-2507", "model_id": "[\"Qwen\",\"qwen3-235b-a22b-2507\"]", "model_name": "qwen3-235b-a22b-2507", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-235b-a22b-2507", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-235b-a22b-2507", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "264.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 264.0, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-32b", "model_id": "[\"Qwen\",\"qwen3-32b\"]", "model_name": "qwen3-32b", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-32b", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-32b", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "725.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 725.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-coder", "model_id": "[\"Qwen\",\"qwen3-coder\"]", "model_name": "qwen3-coder", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-coder", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-coder", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "326.3", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 326.3, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-vl-235b-a22b-thinking", "model_id": "[\"Qwen\",\"qwen3-vl-235b-a22b-thinking\"]", "model_name": "qwen3-vl-235b-a22b-thinking", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-vl-235b-a22b-thinking", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-vl-235b-a22b-thinking", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "602.8", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 602.8, "value_kind": "number"}, {"benchmark_id": "yapbench", "comparable_group": "[\"model-reports:yapbench\",\"yapbench_v0.1\",\"standard mode\"]", "date_precision": "document_publication", "document_id": "model_reports:yapbench_v0_1_paper_leaderboard", "instrument": "yapbench_v0.1", "key": "model-reports:yapbench", "measured_by": "YapBench authors", "measurement_kind": "benchmark_publisher_run", "model": "qwen3-vl-8b-instruct", "model_id": "[\"Qwen\",\"qwen3-vl-8b-instruct\"]", "model_name": "qwen3-vl-8b-instruct", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-vl-8b-instruct", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000qwen3-vl-8b-instruct", "organization": "Qwen", "protocol": "standard mode", "rank_in_source_response": null, "raw_value": "518.0", "read_from": "pdf_text", "reported_at": "2026-01-02", "reported_by": "third_party", "reported_date": "2026-01-02", "series_id": "model_reports:yapbench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "yapbench_v0_1_paper_leaderboard", "source_title": "YapBench v0.1 full leaderboard (Table 6)", "source_url": "https://arxiv.org/abs/2601.00624", "value": 518.0, "value_kind": "number"}], "series": {"declared_max": null, "direction": "lower_is_better", "direction_basis": "reported_metric", "display_scale": null, "first_score_record": {"date_precision": "document_publication", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-haiku-4.5 (reasoning)", "reported_at": "2026-01-02", "source_url": "https://arxiv.org/abs/2601.00624"}, "first_score_report": {"date_precision": "document_publication", "obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000reasoning mode\u0000claude-haiku-4.5 (reasoning)", "reported_at": "2026-01-02", "source_url": "https://arxiv.org/abs/2601.00624"}, "key": "model-reports:yapbench", "max_score_contradicted": false, "metric": "YapIndex", "observation_count": 76, "observed_max": 1427.0, "score_summary": {"display_max": 1427.0, "display_multiplier": 1, "model_count": 76, "model_count_basis": "source_model_id", "numeric_count": 76, "raw_max": 1427.0, "raw_min": 22.7, "source_reference": {"obs_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.5", "observation_id": "curated\u0000yapbench\u0000yapbench_v0_1_paper_leaderboard\u0000yapbench_v0.1\u0000standard mode\u0000glm-4.5", "reported_at": "2026-01-02", "reported_date": "2026-01-02", "source_id": "yapbench_v0_1_paper_leaderboard", "source_url": "https://arxiv.org/abs/2601.00624"}, "unit": "characters"}, "series_id": "model_reports:yapbench:default", "unit": "characters"}}}, "siblings": []}
