{
  "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
}