@llama_index
RT @jerryjliu0: We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals aga…
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"score": 0.36,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.06000000000000001,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-10-26T00:02:03.015420",
"import_source": "api_import",
"source_tagged_at": "2026-10-26T00:02:03.015429",
"enriched": true,
"enriched_at": "2026-10-26T00:02:03.015430"
}🔧 Raw API Response
{
"type": "tweet",
"id": "2114445189590987076",
"url": "https://x.com/llama_index/status/2114445189590987076",
"twitterUrl": "https://twitter.com/llama_index/status/2114445189590987076",
"text": "RT @jerryjliu0: We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing.\n\n✅ It contains comprehensive evals aga…",
"source": "",
"retweetCount": 6,
"replyCount": 24,
"likeCount": 89,
"quoteCount": 3,
"viewCount": 5355,
"createdAt": "Sun Oct 25 19:53:12 +0000 2026",
"lang": "en",
"bookmarkCount": 74,
"isReply": false,
"inReplyToId": null,
"conversationId": "2114445189590987076",
"displayTextRange": [
0,
140
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "llama_index",
"url": "https://x.com/llama_index",
"twitterUrl": "https://twitter.com/llama_index",
"id": "1604278358296055808",
"name": "LlamaIndex 🦙",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
"coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1776721175",
"description": "",
"location": "",
"followers": 121924,
"following": 39,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Sun Dec 18 00:52:44 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1673,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1994,
"statusesCount": 4080,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "Turn any doc into AI-ready context. The AI research lab for document parsing and extraction. Developer-first APIs.\n\nLlamaParse: https://t.co/yQGTiRSfFL",
"entities": {
"description": {
"urls": [
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"indices": [
128,
151
],
"url": "https://t.co/yQGTiRSfFL"
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"indices": [
0,
23
],
"url": "https://t.co/epzefqPT9Z"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"user_mentions": [
{
"id_str": "369777416",
"indices": [
3,
14
],
"name": "Jerry Liu",
"screen_name": "jerryjliu0"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": {
"type": "tweet",
"id": "2114404538652217370",
"url": "https://x.com/jerryjliu0/status/2114404538652217370",
"twitterUrl": "https://twitter.com/jerryjliu0/status/2114404538652217370",
"text": "We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing.\n\n✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md.\n\n✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing.\n\n✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models.\n\n✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals!\n\nCheck it out: https://t.co/DX1bSISNP1\n\nOther links are in our blog! https://t.co/PRxvOFmlVH",
"source": "",
"retweetCount": 6,
"replyCount": 24,
"likeCount": 89,
"quoteCount": 3,
"viewCount": 5355,
"createdAt": "Sun Oct 25 17:11:40 +0000 2026",
"lang": "en",
"bookmarkCount": 74,
"isReply": false,
"inReplyToId": null,
"conversationId": "2114404538652217370",
"displayTextRange": [
0,
266
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "jerryjliu0",
"url": "https://x.com/jerryjliu0",
"twitterUrl": "https://twitter.com/jerryjliu0",
"id": "369777416",
"name": "Jerry Liu",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
"coverPicture": "",
"description": "",
"location": "",
"followers": 86846,
"following": 1624,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Sep 07 22:54:31 +0000 2011",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 11046,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1719,
"statusesCount": 7939,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {
"label": {
"badge": {
"url": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_bigger.png"
},
"description": "LlamaIndex 🦙",
"url": {
"url": "https://twitter.com/llama_index",
"url_type": "DeepLink"
},
"user_label_display_type": "Badge",
"user_label_type": "BusinessLabel"
}
},
"possiblySensitive": false,
"pinnedTweetIds": [
"2107864677611139096"
],
"profile_bio": {
"description": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\n\nLlamaParse: https://t.co/XYZmx5TFz8\nEnterprise: https://t.co/Ht5jwxSrQB",
"entities": {
"description": {
"urls": [
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"indices": [
74,
97
],
"url": "https://t.co/XYZmx5TFz8"
},
{
"display_url": "llamaindex.ai/contact",
"expanded_url": "https://www.llamaindex.ai/contact",
"indices": [
110,
133
],
"url": "https://t.co/Ht5jwxSrQB"
}
],
"user_mentions": [
{
"id_str": "",
"indices": [
33,
45
],
"name": "",
"screen_name": "llama_index"
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"indices": [
0,
23
],
"url": "https://t.co/YiIfjVlzb6"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"display_url": "pic.x.com/BLF5MlFGx7",
"expanded_url": "https://x.com/jerryjliu0/status/2114404538652217370/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2114404413582282752",
"indices": [
267,
290
],
"media_key": "13_2114404413582282752",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAAR1X35yPFxAAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHVffnI8XEAAAAA==",
"media_key": "13_2114404413582282752"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2114404413582282752/img/upvdHmJq5_nj66kr.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "video",
"url": "https://t.co/BLF5MlFGx7",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 32500,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video-s.twimg.com/amplify_video/2114404413582282752/pl/ydh7p023RsHPnC9h.m3u8?tag=29"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2114404413582282752/vid/avc1/480x270/LzJLTOMn74uY9sOG.mp4?tag=29"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2114404413582282752/vid/avc1/640x360/yQKUV6NMrLB_8hZR.mp4?tag=29"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2114404413582282752/vid/avc1/1280x720/XwxXmxUfUhsxrkst.mp4?tag=29"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/amplify_video/2114404413582282752/vid/avc1/1920x1080/Pf1cy5U8xVvEWI25.mp4?tag=29"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "llamaindex.ai/ocria/ocria-1-…",
"expanded_url": "https://www.llamaindex.ai/ocria/ocria-1-technical-report.pdf",
"indices": [
806,
829
],
"url": "https://t.co/DX1bSISNP1"
},
{
"display_url": "llamaindex.ai/blog/parse-ocr…",
"expanded_url": "https://www.llamaindex.ai/blog/parse-ocria-1",
"indices": [
860,
883
],
"url": "https://t.co/PRxvOFmlVH"
}
],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2113291928292790725",
"url": "https://x.com/jerryjliu0/status/2113291928292790725",
"twitterUrl": "https://twitter.com/jerryjliu0/status/2113291928292790725",
"text": "Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. \n\nIt not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-Tab (84.1), and fr-bench-pdf2md (72.1).\n\nOCRia-1 is really, really good at parsing complex tables: nested headers, merged cells, irregular grids, scanned tables, and more. It is also fantastic at parsing complex unlabeled charts (line, bar, pie, technical diagrams), and preserving complex formatting. Most real-world enterprise documents contain at least one of the these, whether it’s a big tax withholding table or a public economic report.\n\nIt is a 4B model and outperforms all other models within a similar parameter class: LightOnOCR-3, Chandra-OCR 2, Mistral OCR 4.1, and more. It is also extremely fast.\n\nAll credit goes to our research team, who spent countless hours on curating a diverse dataset, tuning our training pipeline, and squeezing every last drop out of model optimization so that it can process billions of pages at scale. \n\nOCRia-1 as a base is powering all of our modes within LlamaParse (cost-effective, agentic, agentic plus), so you can access its capabilities today! \n\nIf you’re processing millions/billions of documents at scale, we’re offering enterprises that book a demo up to $3k in credits for a guided evaluation.**\n\n*olmOCR-bench scores are adjusted based on unifying rendering at 1,288px for all models \n**enterprise POC credits apply to eligible organizations that book a demo",
"source": "",
"retweetCount": 109,
"replyCount": 114,
"likeCount": 907,
"quoteCount": 30,
"viewCount": 80796,
"createdAt": "Thu Oct 22 15:30:33 +0000 2026",
"lang": "en",
"bookmarkCount": 790,
"isReply": false,
"inReplyToId": null,
"conversationId": "2113291928292790725",
"displayTextRange": [
0,
270
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "jerryjliu0",
"url": "https://x.com/jerryjliu0",
"twitterUrl": "https://twitter.com/jerryjliu0",
"id": "369777416",
"name": "Jerry Liu",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
"coverPicture": "",
"description": "",
"location": "",
"followers": 86846,
"following": 1624,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Sep 07 22:54:31 +0000 2011",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 11046,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1719,
"statusesCount": 7939,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {
"label": {
"badge": {
"url": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_bigger.png"
},
"description": "LlamaIndex 🦙",
"url": {
"url": "https://twitter.com/llama_index",
"url_type": "DeepLink"
},
"user_label_display_type": "Badge",
"user_label_type": "BusinessLabel"
}
},
"possiblySensitive": false,
"pinnedTweetIds": [
"2107864677611139096"
],
"profile_bio": {
"description": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\n\nLlamaParse: https://t.co/XYZmx5TFz8\nEnterprise: https://t.co/Ht5jwxSrQB",
"entities": {
"description": {
"urls": [
{
"display_url": "cloud.llamaindex.ai",
"expanded_url": "https://cloud.llamaindex.ai/",
"indices": [
74,
97
],
"url": "https://t.co/XYZmx5TFz8"
},
{
"display_url": "llamaindex.ai/contact",
"expanded_url": "https://www.llamaindex.ai/contact",
"indices": [
110,
133
],
"url": "https://t.co/Ht5jwxSrQB"
}
],
"user_mentions": [
{
"id_str": "",
"indices": [
33,
45
],
"name": "",
"screen_name": "llama_index"
}
]
},
"url": {
"urls": [
{
"display_url": "llamaindex.ai",
"expanded_url": "https://www.llamaindex.ai/",
"indices": [
0,
23
],
"url": "https://t.co/YiIfjVlzb6"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null,
"protected": false
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"display_url": "pic.x.com/ECb4n3o1ha",
"expanded_url": "https://x.com/jerryjliu0/status/2113291928292790725/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2113291822562721792",
"indices": [
271,
294
],
"media_key": "7_2113291822562721792",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAwoAAR1T67dGlsAACgACHVPrz+SXkcUAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAADCgABHVPrt0aWwAAKAAIdU+vP5JeRxQAA",
"media_key": "7_2113291822562721792"
}
},
"media_url_https": "https://pbs.twimg.com/ext_tw_video_thumb/2113291822562721792/pu/img/aFE0Q04DhH_id6Io.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "video",
"url": "https://t.co/ECb4n3o1ha",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 52733,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video-s.twimg.com/ext_tw_video/2113291822562721792/pu/pl/fWS6URxsA8rkbweo.m3u8?tag=12&v=da0"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/ext_tw_video/2113291822562721792/pu/vid/avc1/480x270/2j4-NL0QIu81zjWY.mp4?tag=12"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/ext_tw_video/2113291822562721792/pu/vid/avc1/640x360/PT7oxgFDQvfLmlS0.mp4?tag=12"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video-s.twimg.com/ext_tw_video/2113291822562721792/pu/vid/avc1/1280x720/SAhr35kniTRlZfvw.mp4?tag=12"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"isLimitedReply": false,
"communityInfo": null,
"article": null
}