{"data":{"schema_version":"model_decision_evidence.v1","snapshot_date":"2026-09-25","model":{"model":"gpt-image-2.5-sunburst","direct_answer":"GPT Image 2.5 Sunburst is OpenAI's closed-weight image generation and editing model for workflows where editing precision matters most, released on 2026-09-08 alongside Flare, which OpenAI positions for fast everyday generation. It takes text and up to 16 reference images and outputs images up to 3840x2160; OpenAI still cautions that repeated edits can change details you meant to keep, and the reviewed stress test held up through five chained edits.","verified_at":"2026-09-24","model_card":{"context_window":"Not published; prompts are limited to 32,000 characters","max_output":"1 to 10 images per request, up to 3840x2160 each (sizes above 2560x1440 are experimental)","modalities":"Text and image input (up to 16 reference images when editing); image output","parameter_count":"Not disclosed"},"official_sources":[{"title":"Introducing ChatGPT Images 2.5","publisher":"OpenAI","url":"https://openai.com/index/introducing-chatgpt-images-2-5/","retrieved_at":"2026-09-24"},{"title":"GPT-Image-2.5 Sunburst model documentation","publisher":"OpenAI","url":"https://developers.openai.com/api/docs/models/gpt-image-2.5-sunburst","retrieved_at":"2026-09-24"},{"title":"Image prompting guide","publisher":"OpenAI","url":"https://developers.openai.com/api/docs/guides/image-prompting","retrieved_at":"2026-09-24"},{"title":"ChatGPT Images 2.5 System Card","publisher":"OpenAI","url":"https://deploymentsafety.openai.com/chatgpt-images-2-5","retrieved_at":"2026-09-24"}],"open_weights":{"status":"not_available","summary":"OpenAI publishes no GPT Image 2.5 weights. Sunburst is served through the Image API (generations and edits) and the Responses API image generation tool.","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-image-2.5-sunburst","https://developers.openai.com/api/docs/changelog"],"verified_at":"2026-09-24","agent_recipe":""},"curated_comparisons":[],"open_weight_alternatives":[],"reviews":[{"id":"x-alecwilcock-repeat-edits-2026-09","platform":"X","evidence_type":"task_test","title":"Repeated edits to one image with GPT Image 2.5 Sunburst","url":"https://x.com/alecwilcock/status/2100555617941307601","published_at":"2026-09-17","retrieved_at":"2026-09-24","verified_at":"2026-09-24","author":{"name":"Alec Wilcock","handle":"@alecwilcock","profile_url":"https://x.com/alecwilcock","description":"AI educator and content creator whose profile lists a social-media role at ElevenLabs"},"task":"Change the t-shirt in a photo, then feed each output back in as the next input","method":"Chained edits of the same image with one prompt per round, shown in a video.","finding":"The image still held up at round five; the author says the video does not flatter the model, but that other models rarely get past round three before breaking down.","limitation":"One chain of edits judged by eye; the comparison with other models is asserted, not shown; the author works in social media at ElevenLabs.","metrics":[{"label":"Rounds shown","value":"5"}]}]},"ranking":{"name":"gpt-image-2.5-sunburst","display_name":"GPT Image 2.5 Sunburst","vendor":"OpenAI","origin":"intl","category":"image","release_date":"2026-09-08","on_chinaapi":true,"sources":[{"leaderboard":"lmarena_t2i","metric":"Arena score (Elo)","value":"1424","entry":"gpt-image-2.5-sunburst","url":"https://arena.ai/leaderboard/text-to-image","retrieved_at":"2026-10-05","interval":"±8","samples":10884},{"leaderboard":"lmarena_image_edit","metric":"Arena score (Elo)","value":"1522","entry":"gpt-image-2.5-sunburst","url":"https://arena.ai/leaderboard/image-edit","retrieved_at":"2026-10-05","interval":"±5","samples":47289},{"leaderboard":"aa_image_t2i","metric":"Elo","value":"1179","entry":"GPT Image 2.5 Sunburst (max)","url":"https://artificialanalysis.ai/image/leaderboard/text-to-image","retrieved_at":"2026-09-13","interval":"-11/11","samples":5159},{"leaderboard":"aa_image_edit","metric":"Elo","value":"1167","entry":"GPT Image 2.5 Sunburst (max)","url":"https://artificialanalysis.ai/image/leaderboard/editing","retrieved_at":"2026-09-13","interval":"-10/10","samples":5216}],"notes":"Sunburst and Flare are distinct builds; their scores are not interchangeable.","reference_metrics":[{"kind":"price","task":"text_to_image","value":"210.7","unit":"USD / 1,000 images","operator":"Artificial Analysis","provider":"OpenAI","entry":"GPT Image 2.5 Sunburst (max)","conditions":"1024×1024; creator API; default settings (AA pricing footnote)","url":"https://artificialanalysis.ai/image/leaderboard/text-to-image","retrieved_at":"2026-09-13"},{"kind":"price","task":"image_editing","value":"210.7","unit":"USD / 1,000 images","operator":"Artificial Analysis","provider":"OpenAI","entry":"GPT Image 2.5 Sunburst (max)","conditions":"1024×1024; creator API; default settings (AA pricing footnote)","url":"https://artificialanalysis.ai/image/leaderboard/editing","retrieved_at":"2026-09-13"},{"kind":"generation_time","task":"text_to_image","value":"112.476080179214","unit":"seconds","operator":"Artificial Analysis","provider":"OpenAI","entry":"GPT Image 2.5 Sunburst (max), OpenAI","conditions":"1024×1024 or nearest supported; 1 image; 3-day median; includes download","url":"https://artificialanalysis.ai/image/models","retrieved_at":"2026-09-13"}]},"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}