{"data":{"schema_version":"model_decision_evidence.v1","snapshot_date":"2026-09-25","model":{"model":"gpt-6-luna","direct_answer":"GPT-6 Luna is OpenAI's closed-weight model for focused, high-volume tasks, released on 2026-09-22 alongside GPT-6 Sol, with a 1,050,000-token context window (922,000 input), 128,000 output tokens and text and image input. Reviewed tests find it very cheap and fast: it scored 51.99 at max reasoning on AI Coding Daily's leaderboard for about $0.03 a run, close to GPT-6 Sol, while kzhu's test gave it 40/60 and one one-prompt comparison judged its output a flop.","verified_at":"2026-09-24","model_card":{"context_window":"1,050,000 tokens (up to 922,000 input)","max_output":"128,000 tokens","modalities":"Text and image input; text output","parameter_count":"Not disclosed"},"official_sources":[{"title":"GPT-6 Luna model documentation","publisher":"OpenAI","url":"https://developers.openai.com/api/docs/models/gpt-6-luna","retrieved_at":"2026-09-24"},{"title":"OpenAI API changelog","publisher":"OpenAI","url":"https://developers.openai.com/api/docs/changelog","retrieved_at":"2026-09-24"},{"title":"GPT-6 Astra System Card (appendix on GPT-6 Sol and GPT-6 Luna)","publisher":"OpenAI","url":"https://deploymentsafety.openai.com/gpt-6-astra","retrieved_at":"2026-09-24"}],"open_weights":{"status":"not_available","summary":"OpenAI publishes no GPT-6 Luna weights. The model is served through the OpenAI API (Responses, Chat Completions and Batch) and on Amazon Bedrock in us-east-1.","repository":"","licence":"Proprietary hosted model","hardware":"Not applicable","recommended_runtime":"ChinaAPI or the OpenAI API","source_urls":["https://developers.openai.com/api/docs/models/gpt-6-luna","https://developers.openai.com/api/docs/guides/amazon-bedrock"],"verified_at":"2026-09-24","agent_recipe":""},"curated_comparisons":["gpt-6-sol","gpt-6-astra"],"open_weight_alternatives":["deepseek-flash","mimo-v2.6-flash"],"reviews":[{"id":"x-xueyu-svg-quota-2026-09","platform":"X","evidence_type":"task_test","title":"GPT-6 Astra, Sol and Luna on one SVG animation prompt","url":"https://x.com/xueyu1125/status/2102692499710193960","published_at":"2026-09-23","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"雪瑜","handle":"@xueyu1125","profile_url":"https://x.com/xueyu1125","description":"Programmer and AI-tools builder on X who posted the timings and quota readings"},"task":"Generate an SVG animation of a pelican riding a bicycle, shown in H5","method":"Same prompt on GPT-6 Astra, GPT-6 Sol, GPT-6 Luna and GPT-5.6 Sol; the author recorded time taken and the share of a five-hour subscription quota each used.","finding":"GPT-6 Luna was the quickest and lightest of the four at 2 min 18 s and 1% of the five-hour quota, but the author dismissed its result as a flop (“拉完了”), ranking it alongside MiMo-V2.6-Flash.","limitation":"One prompt judged by the author without a score; the quota shares are a subscription meter, not API cost. X's automatic translation renders the verdict as its opposite, so read the original Chinese.","metrics":[{"label":"Time","value":"2 min 18 s"},{"label":"Five-hour quota used","value":"1%"}]},{"id":"x-bridgebench-lava-lamp-2026-09","platform":"X","evidence_type":"task_test","title":"Four models build a lava lamp from one prompt","url":"https://x.com/bridgebench/status/2102770788319310302","published_at":"2026-09-23","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"Bridgebench","handle":"@bridgebench","profile_url":"https://x.com/bridgebench","description":"BridgeMind's benchmark account, which calls itself the official AI benchmark of the vibe coding movement"},"task":"Build a lava lamp from a single prompt","method":"Same prompt on Claude Opus 5.5, GPT-6 Astra, GPT-6 Sol and GPT-6 Luna; the account reported cost and time, asked readers which did best and commented on their answers in replies.","finding":"GPT-6 Luna cost under $0.01 and took 43 seconds, the cheapest and fastest of the four (Claude Opus 5.5: $1.27 and 9 min 35 s); the account left the quality verdict to readers.","limitation":"One prompt with the quality verdict left mostly to readers; the account is BridgeMind's own benchmark and does not say how the models were accessed.","metrics":[{"label":"GPT-6 Luna","value":"\u003c$0.01 · 43 s"}]},{"id":"x-spac89-luna-chip-bench-2026-09","platform":"X","evidence_type":"task_test","title":"GPT-6 Luna at max reasoning on a personal chip benchmark","url":"https://x.com/SPAC89/status/2102726794583359996","published_at":"2026-09-23","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"Iam_","handle":"@SPAC89","profile_url":"https://x.com/SPAC89","description":"X user who follows LLM releases and runs a personal chip benchmark"},"task":"The author's chip benchmark","method":"Run on GPT-6 Luna at max reasoning in ChatGPT and compared with GPT-6 Astra; the author reported time, usage and how the model worked.","finding":"GPT-6 Luna at max reasoning searched for and generated its own images, launched about 15 sub-agents to research and judge the result, and took almost twice as long as Astra while using about 1% of the weekly usage on the ChatGPT x20 plan; the author expects to make it their default model.","limitation":"The benchmark and its scoring are not described and no score is given; usage is a subscription meter, not API cost.","metrics":[{"label":"Weekly usage","value":"About 1% (ChatGPT x20)"},{"label":"Sub-agents","value":"About 15"}]},{"id":"aicodingdaily-llm-coding-leaderboard-2026-09","platform":"Independent benchmark","evidence_type":"independent_suite","title":"AI Coding Daily LLM Coding Leaderboard","url":"https://aicodingdaily.com/leaderboard","published_at":"2026-09-24","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"AI Coding Daily","handle":"@AICodingDaily","profile_url":"https://www.youtube.com/@AICodingDaily","description":"Coding-model testing channel and website that runs its own leaderboard and sells premium tutorials and channel advertising"},"task":"Implement and harden production-shaped projects in several stacks, including a Laravel app, a Go service and a React/TypeScript app, from the same prompts","method":"Each model and reasoning setting is a separate row run in a coding harness, with the average cost and time per run. Code quality is graded by a judge model against a published 100-point rubric and scaled to 20 points per project; behavioural reliability runs each of four projects five times and scores the checks every attempt fails.","finding":"GPT-6 Luna scored 51.99 at max reasoning for about $0.03 and 11 min per run in Codex CLI, 11th of 47 rows and just above GPT-5.6 Luna at max (51.13); at medium reasoning it fell to 40.20.","limitation":"One author's benchmark whose code-quality half is graded by a judge model; rows run in different harnesses, the page is updated as models are added (read on 2026-09-24, 47 rows), and the author sells premium tutorials and advertising.","metrics":[{"label":"Points (max)","value":"51.99"},{"label":"Rank","value":"11 of 47"},{"label":"Cost per run","value":"$0.03"}]},{"id":"techgogogo-kzhu-llm-benchmark-2026-09","platform":"Independent benchmark","evidence_type":"independent_suite","title":"kzhu's six-question LLM test leaderboard","url":"https://www.techgogogo.com/llm-benchmark/","published_at":"2026-09-24","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"AI产品狙击手 kzhu","handle":"@kevinzhu9305","profile_url":"https://www.youtube.com/@kevinzhu9305","description":"Chinese YouTube reviewer who scores models on a six-question test and publishes every score with per-question notes"},"task":"Six questions scored out of 10: constrained sentence writing, two reasoning puzzles (replaced by pelican and compound-bow SVG animations in version 2.2), a browser OS with a space shooter, a 3D racing game and a Trello-style board","method":"Each row names the harness the model ran in (Pi, Claude Code, WorkBuddy and others) and the date; the author scores every question with a note, and warns that totals are only comparable within one test version.","finding":"GPT-6 Luna scored 40/60 on version 2.2 in Pi (the author's note says 41): full marks on the constrained sentences, but physically wrong SVG animations (4 and 6), a flat 2D space shooter, a cluttered racing track and small text on the Trello board.","limitation":"One author's scores on six questions; rows use different harnesses and test versions (2.1 or 2.2), and a few rows' table total differs by one point from the author's note.","metrics":[{"label":"Score","value":"40 / 60 (v2.2, Pi)"}]}]},"ranking":{"name":"gpt-6-luna","display_name":"GPT-6 Luna","vendor":"OpenAI","origin":"intl","category":"text","release_date":"2026-09-22","on_chinaapi":true,"sources":[{"leaderboard":"lmarena_text","metric":"Arena score (Elo)","value":"1443","entry":"gpt-6-luna-max","url":"https://arena.ai/leaderboard/text","retrieved_at":"2026-10-05","interval":"±7","samples":10014},{"leaderboard":"lmarena_text_chinese","metric":"Arena score (Elo)","value":"1484","entry":"gpt-6-luna-max","url":"https://arena.ai/leaderboard/text/chinese","retrieved_at":"2026-10-05","interval":"±21","samples":782},{"leaderboard":"lmarena_text_coding","metric":"Arena score (Elo)","value":"1512","entry":"gpt-6-luna-max","url":"https://arena.ai/leaderboard/text/coding","retrieved_at":"2026-10-05","interval":"±12","samples":2346},{"leaderboard":"aa_index","metric":"Intelligence Index","value":"37","entry":"GPT-6 Luna (max)","url":"https://artificialanalysis.ai/leaderboards/models","retrieved_at":"2026-09-22"},{"leaderboard":"aa_speed","metric":"Median output tokens/s","value":"157","entry":"GPT-6 Luna (max)","url":"https://artificialanalysis.ai/leaderboards/models","retrieved_at":"2026-09-22"},{"leaderboard":"aa_gdpval","metric":"Agentic Real-World Work Tasks, (Elo-500)/2000 (%)","value":"43","entry":"GPT-6 Luna (max)","url":"https://artificialanalysis.ai/leaderboards/models","retrieved_at":"2026-09-22"},{"leaderboard":"aa_tbench_v40","metric":"Agentic Coding \u0026 Terminal Use (%)","value":"13","entry":"GPT-6 Luna (max)","url":"https://artificialanalysis.ai/leaderboards/models","retrieved_at":"2026-09-22"},{"leaderboard":"vals_index","metric":"Accuracy (GDP-weighted finance, coding, legal and tax)","value":"52.32","entry":"GPT-6 Luna","url":"https://www.vals.ai/benchmarks/vals_index","retrieved_at":"2026-10-23","interval":"±1.12"}],"notes":"Released 2026-09-22 per OpenAI's announcement (Introducing GPT-6 Sol and Luna) and the API changelog entry of the same day. LiveBench 1.0 scores were withdrawn on 2026-10-23 after the site moved them into its historical-release view and launched the incompatible LiveBench 2.0 categories."},"sources":{"aa_gdpval":{"id":"aa_gdpval","name":"Artificial Analysis · GDPval-AA v2.1","operator":"Artificial Analysis","metric":"Agentic Real-World Work Tasks, (Elo-500)/2000 (%)","url":"https://artificialanalysis.ai/leaderboards/models","edition":"GDPval-AA v2.1, live board, read 2026-09-22. 220 agentic task-completion tasks with file outputs, ranked pairwise by a panel of three frontier LLM judges; since v2.1 the Elo scale is anchored to DeepSeek V4.1 Flash (max) at 1600 and fitted with a Crowd-BT model, so its figures are not comparable with the v2 figures this page quoted from its 2026-09-12 read. The column prints clamp((Elo-500)/2000). It carries 10% of the Agents category inside Intelligence Index v4.3.2, so this column is a component of the AA Intelligence Index shown as an individual source, not an independent operator. Rows Artificial Analysis marks deprecated are read with the leaderboard's Status filter set to All (CA-948). The column is hidden until the leaderboard's Intelligence group is expanded","retrieved_at":"2026-09-22","scene":"agent_work"},"aa_image_edit":{"id":"aa_image_edit","name":"Artificial Analysis Editing","operator":"Artificial Analysis","metric":"Elo","url":"https://artificialanalysis.ai/image/leaderboard/editing","edition":"live board; exact row settings retained","retrieved_at":"2026-09-13","task":"image_editing"},"aa_image_t2i":{"id":"aa_image_t2i","name":"Artificial Analysis Text To Image","operator":"Artificial Analysis","metric":"Elo","url":"https://artificialanalysis.ai/image/leaderboard/text-to-image","edition":"live board; exact row settings retained","retrieved_at":"2026-09-13","task":"text_to_image"},"aa_index":{"id":"aa_index","name":"Artificial Analysis Intelligence Index","operator":"Artificial Analysis","metric":"Intelligence Index","url":"https://artificialanalysis.ai/leaderboards/models","edition":"Intelligence Index v4.3.2, read 2026-09-22; its figures are not comparable with the v4.3 figures this page quoted from its 2026-09-12 read. v4.3.1 refreshed the pairwise judge panels of AA-Briefcase and GDPval-AA, and v4.3.2 moved GDPval-AA to v2.1 (Elo scale anchored to DeepSeek V4.1 Flash (max) at 1600, fitted with a Crowd-BT model) and refitted AA-Briefcase v1.1 with Crowd-BT, so rows moved without any model changing. v4.3 had already swapped τ³-Banking out of the index for AutomationBench-AA and Terminal-Bench v2.1 for v4.0. The leaderboard's default Status: Current filter hides rows Artificial Analysis marks deprecated; they still render with Status set to All and are re-read from that view like any other row (CA-948). A trailing * is reproduced as the board prints it: the board's data marks that score as estimated (intelligenceIndexIsEstimated), i.e. not every evaluation in the index had been run for that model","retrieved_at":"2026-09-22"},"aa_mlcr":{"id":"aa_mlcr","name":"Artificial Analysis · MLCR-AA","operator":"Artificial Analysis","metric":"Medical Long Context Reasoning (%)","url":"https://artificialanalysis.ai/evaluations/mlcr-aa","edition":"MLCR-AA, live board, read 2026-09-22. Artificial Analysis marks it a standalone evaluation that is NOT part of Intelligence Index v4.3 — unlike the GDPval-AA v2 and Terminal-Bench v4.0 columns, this one is not a component of the AA Intelligence Index shown as an individual source, only the same operator. The underlying benchmark is Wisedocs' open MLCR (Wisedocs-AI/medical-long-context-reasoning): synthetic medical records of roughly 25,000-64,000 tokens, graded across six tiers from locating a single fact to expert-level clinical synthesis. It measures multi-document reasoning over long records, not medical capability in general. The main leaderboard carries no column for it; the figures were first read off the evaluation page's chart (2026-09-07) and since 2026-09-22 from the per-model pages' payload, which carries every model the chart can show (CA-956)","retrieved_at":"2026-09-22","scene":"medical"},"aa_speed":{"id":"aa_speed","name":"Artificial Analysis · Output Speed","operator":"Artificial Analysis","metric":"Median output tokens/s","url":"https://artificialanalysis.ai/leaderboards/models","edition":"live board; measured by Artificial Analysis against the vendor's own API, not through ChinaAPI. Rows Artificial Analysis marks deprecated are read with the leaderboard's Status filter set to All (CA-948)","retrieved_at":"2026-09-22","scene":"speed"},"aa_tbench_v40":{"id":"aa_tbench_v40","name":"Artificial Analysis · Terminal-Bench v4.0","operator":"Artificial Analysis","metric":"Agentic Coding \u0026 Terminal Use (%)","url":"https://artificialanalysis.ai/leaderboards/models","edition":"Terminal-Bench 4.0 (66 tasks), run by Artificial Analysis with the mini-swe-agent harness, pass@1 averaged over 3 repeats per task; read 2026-09-22. When this column replaced the benchmark's own board on 2026-09-07 the methodology page named the harness as mini-SWE-agent v2.4.6; on 2026-09-21 it and the evaluation page name mini-swe-agent without a version, and every figure quoted before then read back unchanged. One harness for every model, so the column compares models rather than model-plus-best-scaffold — which is why it replaced the benchmark's own board, whose rows are agent × model and covered one Chinese model out of 34 (CA-788, overturning CA-734). It carries 10% of the Coding category inside Intelligence Index v4.3.2, so this column is a component of the AA Intelligence Index shown as an individual source, not an independent operator. Rows Artificial Analysis marks deprecated are read with the leaderboard's Status filter set to All (CA-948). The column is hidden until the leaderboard's Intelligence group is expanded","retrieved_at":"2026-09-22","scene":"agentic"},"aa_video_i2v_audio":{"id":"aa_video_i2v_audio","name":"Artificial Analysis Image To Video · With Audio","operator":"Artificial Analysis","metric":"Elo","url":"https://artificialanalysis.ai/video/leaderboard/image-to-video","edition":"live board; with audio pool; exact row settings retained","retrieved_at":"2026-09-13","task":"image_to_video_audio"},"aa_video_t2v_audio":{"id":"aa_video_t2v_audio","name":"Artificial Analysis Text To Video · With Audio","operator":"Artificial Analysis","metric":"Elo","url":"https://artificialanalysis.ai/video/leaderboard/text-to-video","edition":"live board; with audio pool; exact row settings retained","retrieved_at":"2026-09-13","task":"text_to_video_audio"},"epoch_eci":{"id":"epoch_eci","name":"Epoch Capabilities Index (ECI)","operator":"Epoch AI","metric":"General ECI","url":"https://epoch.ai/eci","edition":"live board","licence":"CC BY 4.0, as labelled on the page (https://creativecommons.org/licenses/by/4.0/)","retrieved_at":"2026-10-04"},"lmarena_i2v":{"id":"lmarena_i2v","name":"LMArena Image-to-Video Arena","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/image-to-video","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (image_to_video, category overall), published 2026-09-22, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","task":"image_to_video","updated_at":"2026-09-22"},"lmarena_image_edit":{"id":"lmarena_image_edit","name":"LMArena Image Edit Arena","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/image-edit","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (image_edit, category overall), published 2026-09-30, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","task":"image_editing","updated_at":"2026-09-30"},"lmarena_t2i":{"id":"lmarena_t2i","name":"LMArena Text-to-Image Arena","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/text-to-image","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (text_to_image, category overall), published 2026-09-24, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","task":"text_to_image","updated_at":"2026-09-24"},"lmarena_t2v":{"id":"lmarena_t2v","name":"LMArena Text-to-Video Arena","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/text-to-video","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (text_to_video, category overall), published 2026-09-22, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","task":"text_to_video","updated_at":"2026-09-22"},"lmarena_text":{"id":"lmarena_text","name":"LMArena Text Arena","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/text","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (text_style_control, category overall), published 2026-10-02, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","updated_at":"2026-10-02"},"lmarena_text_chinese":{"id":"lmarena_text_chinese","name":"LMArena Text Arena · Chinese","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/text/chinese","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (text_style_control, category chinese, prompts in Chinese), published 2026-10-02, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","scene":"chinese","updated_at":"2026-10-02"},"lmarena_text_coding":{"id":"lmarena_text_coding","name":"LMArena Text Arena · Coding","operator":"LMArena (arena.ai)","metric":"Arena score (Elo)","url":"https://arena.ai/leaderboard/text/coding","edition":"Hugging Face dataset lmarena-ai/leaderboard-dataset (text_style_control, category coding), published 2026-10-02, revision 46919c467f7f. Each rating is rounded half-up to a whole number and its interval is rating_upper minus rating, as arena.ai prints them; the dataset carries no Preliminary badge, so each citation records its row's vote count instead, and row names follow the dataset, which can trail a rename on arena.ai","licence":"CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), as labelled on the dataset card (https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)","retrieved_at":"2026-10-05","scene":"coding","updated_at":"2026-10-02"},"superclue":{"id":"superclue","name":"SuperCLUE 智能指数","operator":"SuperCLUE","metric":"总分 (overall)","url":"https://www.superclueai.com/homepage","edition":"2026-07 evaluation, published 2026-08-06. The homepage reads this edition from its data file (/data/generalboard/2026年7月.xlsx, sheet 总排行榜, last modified 2026-09-11), which also carries rows evaluated after publication, each with its own evaluation publication date (the latest 2026-09-11); the page's Latest Update line refers to a different sub-board","retrieved_at":"2026-10-04"},"vals_index":{"id":"vals_index","name":"Vals Index","operator":"Vals AI","metric":"Accuracy (GDP-weighted finance, coding, legal and tax)","url":"https://www.vals.ai/benchmarks/vals_index","edition":"V2.2, page updated 2026-10-22; complete current cohort read 2026-10-23. Finance Agent v2.1 replaces v2 in this index; figures are not comparable with the V2.1 snapshot. Missing exact builds are not carried forward.","retrieved_at":"2026-10-23"},"vendor_card":{"id":"vendor_card","name":"Vendor's own evaluation card","operator":"the model's own vendor","metric":"varies; the benchmark is named in each row","url":"","edition":"self-reported","self_reported":true,"retrieved_at":"2026-09-22"}}},"success":true}