{"id":"deepseek-v4-1-flash-1017","slug":"deepseek-v4-1-flash-1017","name":"DeepSeek V4.1 Flash 1017","orgId":"deepseek","family":"deepseek-v4-1-flash-1017","releaseDate":"2026-10-17","availability":"ga","openWeights":true,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":1048576,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/deepseek_ai/status/2111375640717033777","hfRepo":"deepseek-ai/DeepSeek-V4.1-Flash-1017","modalities":["text","image"],"aliases":["DeepSeek V4.1 Flash 1017","deepseek-v4.1-flash-1017","deepseek-v4-1-flash-1017","deepseek-ai/deepseek-v4.1-flash-1017","deepseek/deepseek-v4.1-flash-1017","DeepSeek: DeepSeek V4.1 Flash 1017","deepseek-v4.1-flash-1017_max","deepseek-v4.1-flash-1017_high","deepseek-v4.1-flash-1017_low","deepseek-v4.1-flash-1017_none","deepseek v4.1 flash 1017"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-17","announced":"2026-10-17","blurb":"A new snapshot of DeepSeek V4.1 Flash. DeepSeek says it posts stronger benchmark results, finishes tasks faster and gives shorter outputs. Tracked separately from the original V4.1 Flash.","api":"live","openWeights":"yes","peer":{"slug":"deepseek-v4-1-flash","label":"DeepSeek V4.1 Flash (original)"},"facts":[{"label":"Snapshot of","value":"DeepSeek V4.1 Flash"},{"label":"Weights","value":"Hugging Face and ModelScope"},{"label":"Available","value":"DeepSeek website, app and API"}],"claims":["Lab claim: stronger benchmark results, faster task completion and shorter outputs than the previous V4.1 Flash."],"pitch":"a Pareto upgrade with stronger benchmarks, faster tasks and shorter outputs","sources":[{"kind":"lab","title":"DeepSeek announcement on X","url":"https://x.com/deepseek_ai/status/2111375640717033777","date":"2026-10-17"},{"kind":"lab","title":"DeepSeek open-weights post on X","url":"https://x.com/deepseek_ai/status/2111375653069259247","date":"2026-10-17"}],"firstBenchmark":{"date":"2026-10-20","benchmarkId":"vals-index"}},"contextSource":"openrouter","organization":{"id":"deepseek","name":"DeepSeek","slug":"deepseek","country":null,"url":null,"color":"#4D6BFE","mark":"DS"},"price":{"modelId":"deepseek-v4-1-flash-1017","provider":"deepseek","inputPerM":null,"outputPerM":null,"blendedPerM":0.5249999999999999,"tokensPerS":null,"observedAt":"2026-11-03","sourceId":"openrouter"},"answer":{"word":"Yes.","scope":"Yes on Coding (best per dollar). Not the overall leader.","lead":"As of Nov 3, 2026, DeepSeek V4.1 Flash 1017 is state of the art on best per dollar in Coding (since Oct 20, 2026; sources Code Migration; methodology v1.0). DeepSeek V4.1 Flash 1017 shares the Coding best-per-dollar frontier with Claude Opus 5.5, Claude Sonnet 5.5, DeepSeek V4.1 Flash, GLM 5.3 Flash since Oct 20, 2026. Co-SOTA shares rank 1.","confidence":"medium"},"status":"BENCHMARKED","verdicts":[{"id":"v_overall_general-llm_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":60,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":33.421750663129984,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #60 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#60 in General LLM"},{"id":"v_open-weights_general-llm_deepseek-v4-1-flash-1017_2026-11-03_open_NEAR_SOTA","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"general-llm","category_name":"General LLM","slice":"open-weights","state":"NEAR_SOTA","rank":2,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":-4.5429666119321155,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Close in General LLM: rank #2, -4.5 percentile points behind the leader.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Near-SOTA · General LLM (open weights)"},{"id":"v_pareto_general-llm_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":57,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":32.18390804597699,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #57 in General LLM on best per dollar.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#57 in General LLM (best per dollar)"},{"id":"v_overall_reasoning_deepseek-v4-1-flash-1017_2026-11-03_open_INSUFFICIENT_DATA","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"gpqa-diamond","name":"GPQA Diamond","rank":17}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"lmarena-text-hard","name":"LMArena Text (style-controlled, hard prompts)"}],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"#17 on GPQA Diamond; missing Humanity's Last Exam and LMArena Text (style-controlled, hard prompts)","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_science_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":17,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Last listed at #17 in Science on 2026-10-17. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#17 in Science"},{"id":"v_open-weights_science_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"science","category_name":"Science","slice":"open-weights","state":"RANKED","rank":1,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #1 in Science. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#1 in Science (open weights)"},{"id":"v_overall_coding_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"coding","category_name":"Coding","slice":"overall","state":"RANKED","rank":8,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":23.919753086419746,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #8 in Coding.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#8 in Coding"},{"id":"v_open-weights_coding_deepseek-v4-1-flash-1017_2026-11-03_open_NEAR_SOTA","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"coding","category_name":"Coding","slice":"open-weights","state":"NEAR_SOTA","rank":2,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":-4.713804713804734,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Close in Coding: rank #2, -4.7 percentile points behind the leader.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Near-SOTA · Coding (open weights)"},{"id":"v_pareto_coding_deepseek-v4-1-flash-1017_2026-10-20_open_CO_SOTA","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"coding","category_name":"Coding","slice":"pareto","state":"CO_SOTA","rank":1,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":0,"confidence":"medium","valid_from":"2026-10-20","valid_to":null,"since_text":"since Oct 20, 2026","configuration":"max","rationale":"DeepSeek V4.1 Flash 1017 shares the Coding best-per-dollar frontier with Claude Opus 5.5, Claude Sonnet 5.5, DeepSeek V4.1 Flash, GLM 5.3 Flash since Oct 20, 2026. Co-SOTA shares rank 1.","safeguard_flags":["pareto","two_signal_confirmed"],"co_sota_with":["claude-opus-5-5","claude-sonnet-5-5","deepseek-v4-1-flash","glm-5-3-flash"],"challengers":[],"methodology":"1.0","label":"Pareto · Coding"},{"id":"v_overall_factuality_deepseek-v4-1-flash-1017_2026-11-03_open_INSUFFICIENT_DATA","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"factuality","category_name":"Factuality","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"simpleqa","name":"SimpleQA Verified","rank":43}],"missing_evidence":[{"benchmark":"lmarena-factuality","name":"LMArena Text factuality"}],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"#43 on SimpleQA Verified; missing LMArena Text factuality","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_arc_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":8,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"high","rationale":"Ranked #8 in Abstraction (ARC). That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#8 in Abstraction (ARC)"},{"id":"v_open-weights_arc_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"arc","category_name":"Abstraction (ARC)","slice":"open-weights","state":"RANKED","rank":1,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"high","rationale":"Ranked #1 in Abstraction (ARC). That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#1 in Abstraction (ARC) (open weights)"},{"id":"v_overall_legal_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"legal","category_name":"Legal","slice":"overall","state":"RANKED","rank":12,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #12 in Legal. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#12 in Legal"},{"id":"v_open-weights_legal_deepseek-v4-1-flash-1017_2026-11-03_open_RANKED","model":"deepseek-v4-1-flash-1017","model_name":"DeepSeek V4.1 Flash 1017","category":"legal","category_name":"Legal","slice":"open-weights","state":"RANKED","rank":4,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #4 in Legal. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#4 in Legal (open weights)"}]}