{"record": {"aliases": ["GoBench", "GoBench 9x9 Go", "GoBench: Evaluating LLMs on the Game of Go"], "artifacts": [{"kind": "website", "url": "https://rolandgao.com/gobench.pdf"}], "categories": ["reasoning"], "description": {"en": "Elo is relative to this 9x9 Go KataGo ladder, with the random player fixed at zero; it is not a percentage or a human Go rank. Track 1 uses APIs without tools, Track 2 evaluates agent-built engines, and Track 3 evaluates tutorial-assisted API play. Context mode, reasoning effort, learning time, engine time limit, and the ladder snapshot affect comparisons. The cited LLM tables have 14-30 games per API configuration or 300 per engine, with 95% confidence intervals reported in the source. Current Track 2 uses a 60-second engine clock, unlike the older agent-in-the-loop paper results."}, "documents": [{"document_type": "benchmark_leaderboard", "id": "model_reports:gobench_live_leaderboard", "model_name": null, "organization": "Roland Gao", "published": null, "retrieved_at": "2026-10-25", "source": "model_reports", "source_id": "gobench_live_leaderboard", "source_url": "https://rolandgao.com/blog/gobench/", "title": "GoBench leaderboard and current track definitions"}, {"document_type": "benchmark_leaderboard", "id": "model_reports:gobench_llm_results_2026_10_19", "model_name": null, "organization": "Roland Gao", "published": "2026-10-19", "retrieved_at": "2026-10-25", "source": "model_reports", "source_id": "gobench_llm_results_2026_10_19", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)"}], "evidence_summary": {"document_count": 2, "model_count": 19, "model_count_basis": "source_model_id"}, "key": "model-reports:gobench", "modality": null, "name": "GoBench", "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://rolandgao.com/gobench.pdf"}, "publisher": null, "released": "2026-09-15", "released_reference": {"basis": "benchmark_release", "source_key": "model-reports:gobench", "source_url": "https://rolandgao.com/gobench.pdf"}, "schema_version": 1, "sizes": [], "slug": "gobench", "source": "model_reports", "source_benchmark_id": "gobench"}, "schema_version": 1, "scores_by_source": {"model_reports": {"rows": [{"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Fable 5.1", "model_id": "[\"Anthropic\",\"Claude Fable 5.1\"]", "model_name": "Claude Fable 5.1", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2122.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2122.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Opus 5", "model_id": "[\"Anthropic\",\"Claude Opus 5\"]", "model_name": "Claude Opus 5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Opus 5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Opus 5", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2076.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2076.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Opus 5.5", "model_id": "[\"Anthropic\",\"Claude Opus 5.5\"]", "model_name": "Claude Opus 5.5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2276.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2276.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Sonnet 5.5", "model_id": "[\"Anthropic\",\"Claude Sonnet 5.5\"]", "model_name": "Claude Sonnet 5.5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Sonnet 5.5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Sonnet 5.5", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2087.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2087.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "DeepSeek-V4-Flash-0731", "model_id": "[\"DeepSeek\",\"DeepSeek-V4-Flash-0731\"]", "model_name": "DeepSeek-V4-Flash-0731", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000DeepSeek-V4-Flash-0731", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000DeepSeek-V4-Flash-0731", "organization": "DeepSeek", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1189.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1189.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "DeepSeek-V4.1-Flash", "model_id": "[\"DeepSeek\",\"DeepSeek-V4.1-Flash\"]", "model_name": "DeepSeek-V4.1-Flash", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash", "organization": "DeepSeek", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1381.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1381.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Luna", "model_id": "[\"OpenAI\",\"GPT-5.6 Luna\"]", "model_name": "GPT-5.6 Luna", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-5.6 Luna", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-5.6 Luna", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1091.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1091.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1846.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1846.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2227.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2227.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Luna", "model_id": "[\"OpenAI\",\"GPT-6 Luna\"]", "model_name": "GPT-6 Luna", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Luna", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Luna", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "830.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 830.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Sol", "model_id": "[\"OpenAI\",\"GPT-6 Sol\"]", "model_name": "GPT-6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1499.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1499.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6.1 Sol", "model_id": "[\"OpenAI\",\"GPT-6.1 Sol\"]", "model_name": "GPT-6.1 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6.1 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6.1 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2172.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2172.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Gemini 3.1 Pro", "model_id": "[\"Google\",\"Gemini 3.1 Pro\"]", "model_name": "Gemini 3.1 Pro", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.1 Pro", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.1 Pro", "organization": "Google", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1797.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1797.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Gemini 3.6 Flash", "model_id": "[\"Google\",\"Gemini 3.6 Flash\"]", "model_name": "Gemini 3.6 Flash", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.6 Flash", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.6 Flash", "organization": "Google", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1336.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1336.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Gemini 3.8 Flash", "model_id": "[\"Google\",\"Gemini 3.8 Flash\"]", "model_name": "Gemini 3.8 Flash", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.8 Flash", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Gemini 3.8 Flash", "organization": "Google", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1616.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1616.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Grok 4.6", "model_id": "[\"xAI\",\"Grok 4.6\"]", "model_name": "Grok 4.6", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Grok 4.6", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Grok 4.6", "organization": "xAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "916.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 916.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Muse Spark 1.3 Contributor", "model_id": "[\"Meta\",\"Muse Spark 1.3 Contributor\"]", "model_name": "Muse Spark 1.3 Contributor", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Muse Spark 1.3 Contributor", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Muse Spark 1.3 Contributor", "organization": "Meta", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1449.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1449.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "gemini-4-argon", "model_id": "[\"Google\",\"gemini-4-argon\"]", "model_name": "gemini-4-argon", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000gemini-4-argon", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000gemini-4-argon", "organization": "Google", "protocol": "Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2353.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2353.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort low; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort low; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort low; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort low; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2301.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2301.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Fable 5.1", "model_id": "[\"Anthropic\",\"Claude Fable 5.1\"]", "model_name": "Claude Fable 5.1", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2269.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2269.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Opus 5", "model_id": "[\"Anthropic\",\"Claude Opus 5\"]", "model_name": "Claude Opus 5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000Claude Opus 5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000Claude Opus 5", "organization": "Anthropic", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2256.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2256.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "DeepSeek-V4-Flash-0731", "model_id": "[\"DeepSeek\",\"DeepSeek-V4-Flash-0731\"]", "model_name": "DeepSeek-V4-Flash-0731", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4-Flash-0731", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4-Flash-0731", "organization": "DeepSeek", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1449.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1449.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "DeepSeek-V4.1-Flash", "model_id": "[\"DeepSeek\",\"DeepSeek-V4.1-Flash\"]", "model_name": "DeepSeek-V4.1-Flash", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash", "organization": "DeepSeek", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1707.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1707.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "DeepSeek-V4.1-Flash-1017", "model_id": "[\"DeepSeek\",\"DeepSeek-V4.1-Flash-1017\"]", "model_name": "DeepSeek-V4.1-Flash-1017", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash-1017", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000DeepSeek-V4.1-Flash-1017", "organization": "DeepSeek", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1634.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1634.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Luna", "model_id": "[\"OpenAI\",\"GPT-5.6 Luna\"]", "model_name": "GPT-5.6 Luna", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-5.6 Luna", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-5.6 Luna", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1058.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1058.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1929.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1929.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2568.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2568.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Luna", "model_id": "[\"OpenAI\",\"GPT-6 Luna\"]", "model_name": "GPT-6 Luna", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Luna", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Luna", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1120.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1120.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Sol", "model_id": "[\"OpenAI\",\"GPT-6 Sol\"]", "model_name": "GPT-6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2006.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2006.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6.1 Sol", "model_id": "[\"OpenAI\",\"GPT-6.1 Sol\"]", "model_name": "GPT-6.1 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6.1 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0\u0000GPT-6.1 Sol", "organization": "OpenAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort max; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2379.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2379.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Grok 4.6", "model_id": "[\"xAI\",\"Grok 4.6\"]", "model_name": "Grok 4.6", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\u0000Grok 4.6", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\u0000Grok 4.6", "organization": "xAI", "protocol": "Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1045.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1045.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Muse Spark 1.3 Contributor", "model_id": "[\"Meta\",\"Muse Spark 1.3 Contributor\"]", "model_name": "Muse Spark 1.3 Contributor", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\u0000Muse Spark 1.3 Contributor", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0\u0000Muse Spark 1.3 Contributor", "organization": "Meta", "protocol": "Track 1; multi-turn API; no tools; reasoning effort xhigh; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "1415.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 1415.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track1_api_2026_10_19\",\"Track 1; single-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track1_api_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; single-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; single-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 1; single-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2011.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2011.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Claude Code; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Opus 5.5", "model_id": "[\"Anthropic\",\"Claude Opus 5.5\"]", "model_name": "Claude Opus 5.5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "organization": "Anthropic", "protocol": "Track 2; Claude Code; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3211.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3211.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "Claude Opus 5.5", "model_id": "[\"Anthropic\",\"Claude Opus 5.5\"]", "model_name": "Claude Opus 5.5", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "organization": "Anthropic", "protocol": "Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3389.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3389.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2609.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2609.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 1h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3063.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3063.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2472.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2472.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3230.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3230.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2388.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2388.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 4h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3313.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3313.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-5.6 Sol", "model_id": "[\"OpenAI\",\"GPT-5.6 Sol\"]", "model_name": "GPT-5.6 Sol", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-5.6 Sol", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2492.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2492.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track2_engine60s_2026_10_19\",\"Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track2_engine60s_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 2; Codex; reasoning effort high; 8h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "3264.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 3264.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track3_tutorial3_3_2026_10_19\",\"Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 1h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track3_tutorial3_3_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 1h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 1h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 1h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2341.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2341.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track3_tutorial3_3_2026_10_19\",\"Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 2h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track3_tutorial3_3_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 2h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 2h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 2h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2550.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2550.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track3_tutorial3_3_2026_10_19\",\"Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 4h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track3_tutorial3_3_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 4h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 4h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 4h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2386.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2386.0, "value_kind": "number"}, {"benchmark_id": "gobench", "comparable_group": "[\"model-reports:gobench\",\"gobench_9x9_track3_tutorial3_3_2026_10_19\",\"Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 8h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\"]", "date_precision": "document_publication", "document_id": "model_reports:gobench_llm_results_2026_10_19", "instrument": "gobench_9x9_track3_tutorial3_3_2026_10_19", "key": "model-reports:gobench", "measured_by": "Roland Gao", "measurement_kind": "benchmark_publisher_run", "model": "GPT-6 Astra", "model_id": "[\"OpenAI\",\"GPT-6 Astra\"]", "model_name": "GPT-6 Astra", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 8h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track3_tutorial3_3_2026_10_19\u0000Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 8h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0\u0000GPT-6 Astra", "organization": "OpenAI", "protocol": "Track 3; multi-turn API; no evaluation tools; reasoning effort high; tutorial3.3 by GPT-6 Astra high in Codex; 8h tutorial development with KataGo; 5000-token tutorial; 7 komi; random-player Elo 0", "rank_in_source_response": null, "raw_value": "2375.0", "read_from": "html_text", "reported_at": "2026-10-19", "reported_by": "third_party", "reported_date": "2026-10-19", "series_id": "model_reports:gobench:default", "source": "model_reports", "source_document_type": "benchmark_leaderboard", "source_id": "gobench_llm_results_2026_10_19", "source_title": "GoBench Track 1-3 LLM comparison tables (2026-10-19)", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255", "value": 2375.0, "value_kind": "number"}], "series": {"declared_max": null, "direction": "higher_is_better", "direction_basis": "reported_metric", "display_scale": null, "first_score_record": {"date_precision": "document_publication", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "reported_at": "2026-10-19", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255"}, "first_score_report": {"date_precision": "document_publication", "obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track1_api_2026_10_19\u0000Track 1; multi-turn API; no tools; reasoning effort high; 7 komi; random-player Elo 0\u0000Claude Fable 5.1", "reported_at": "2026-10-19", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255"}, "key": "model-reports:gobench", "max_score_contradicted": false, "metric": "elo", "observation_count": 47, "observed_max": 3389.0, "score_summary": {"display_max": 3389.0, "display_multiplier": 1, "model_count": 19, "model_count_basis": "source_model_id", "numeric_count": 47, "raw_max": 3389.0, "raw_min": 830.0, "source_reference": {"obs_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "observation_id": "curated\u0000gobench\u0000gobench_llm_results_2026_10_19\u0000gobench_9x9_track2_engine60s_2026_10_19\u0000Track 2; Claude Code; reasoning effort high; 2h engine development; no internet or KataGo during development; code-only evaluation; 60s per game; 7 komi; random-player Elo 0\u0000Claude Opus 5.5", "reported_at": "2026-10-19", "reported_date": "2026-10-19", "source_id": "gobench_llm_results_2026_10_19", "source_url": "https://github.com/RolandGao/gobench/blob/ea88ed944c07dff5d063e7e2789a481818d0dc9c/log/summary/report.txt#L196-L255"}, "unit": "elo"}, "series_id": "model_reports:gobench:default", "unit": "elo"}}}, "siblings": []}