🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

We comprehensively benchmarked Opus 4.7 on document understanding. We evaluated it through ParseBench - our comprehensive OCR benchmark for enterprise documents where we evaluate tables, text, charts, and visual grounding. The results πŸ§‘β€πŸ”¬: - Opus 4.7 is a general improvement over Opus 4.6. It has gotten much better at charts compared to the previous iteration - Opus 4.7 is quite good at tables, though not quite as good as Gemini 3 flash - Opus 4.7 wins on content faithfulness across all techniques (including ours) - Using Opus 4.7 as an OCR solution is expensive at ~7c per page!! For comparison, our agentic mode is 1.25c and cost-effective is ~0.4c by default. Take a look at these results and more on ParseBench! https://t.co/tYiSOMbd6p

Media 1

πŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044902620746363016/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2044902620746363016/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-04-17T02:45:51.363447",
  "pipeline_version": "2.0"
}

πŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2044902620746363016",
  "url": "https://x.com/jerryjliu0/status/2044902620746363016",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2044902620746363016",
  "text": "We comprehensively benchmarked Opus 4.7 on document understanding.\n\nWe evaluated it through ParseBench - our comprehensive OCR benchmark for enterprise documents where we evaluate tables, text, charts, and visual grounding.\n\nThe results πŸ§‘β€πŸ”¬: \n- Opus 4.7 is a general improvement over Opus 4.6. It has gotten much better at charts compared to the previous iteration\n- Opus 4.7 is quite good at tables, though not quite as good as Gemini 3 flash \n- Opus 4.7 wins on content faithfulness across all techniques (including ours) \n- Using Opus 4.7 as an OCR solution is expensive at ~7c per page!! For comparison, our agentic mode is 1.25c and cost-effective is ~0.4c by default. \n\nTake a look at these results and more on ParseBench! https://t.co/tYiSOMbd6p",
  "source": "Twitter for iPhone",
  "retweetCount": 9,
  "replyCount": 2,
  "likeCount": 60,
  "quoteCount": 0,
  "viewCount": 11340,
  "createdAt": "Thu Apr 16 22:15:51 +0000 2026",
  "lang": "en",
  "bookmarkCount": 27,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2044902620746363016",
  "displayTextRange": [
    0,
    278
  ],
  "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": 72848,
    "following": 1470,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8655,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1485,
    "statusesCount": 6855,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "llamaindex.ai/careers",
              "expanded_url": "https://www.llamaindex.ai/careers",
              "indices": [
                71,
                94
              ],
              "url": "https://t.co/EUnMNmbCtx"
            },
            {
              "display_url": "llamaindex.ai/contact",
              "expanded_url": "https://www.llamaindex.ai/contact",
              "indices": [
                107,
                130
              ],
              "url": "https://t.co/Ht5jwxSrQB"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "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
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/nqJfxSlXHp",
        "expanded_url": "https://twitter.com/jerryjliu0/status/2044902620746363016/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2044902473366962176",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2044902473366962176",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxg8/cVWwAACgACHGD0GWXaMIgAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHGDz9xVbAAAKAAIcYPQZZdowiAAA",
            "media_key": "3_2044902473366962176"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HGDz9xVbAAAoP5z.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 427,
              "w": 763,
              "x": 0,
              "y": 0
            },
            {
              "h": 427,
              "w": 427,
              "x": 0,
              "y": 0
            },
            {
              "h": 427,
              "w": 375,
              "x": 0,
              "y": 0
            },
            {
              "h": 427,
              "w": 214,
              "x": 42,
              "y": 0
            },
            {
              "h": 427,
              "w": 1200,
              "x": 0,
              "y": 0
            }
          ],
          "height": 427,
          "width": 1200
        },
        "sizes": {
          "large": {
            "h": 427,
            "w": 1200
          }
        },
        "type": "photo",
        "url": "https://t.co/nqJfxSlXHp"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "parsebench.ai",
        "expanded_url": "https://parsebench.ai/",
        "indices": [
          729,
          752
        ],
        "url": "https://t.co/tYiSOMbd6p"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2044886527352647859",
    "url": "https://x.com/llama_index/status/2044886527352647859",
    "twitterUrl": "https://twitter.com/llama_index/status/2044886527352647859",
    "text": "Anthropic says Opus 4.7 hits 80.6% on Document Reasoning — up from 57.1%.\n\nBut \"reasoning about documents\" ≠ \"parsing documents for agents.\"\n\nWe ran it on ParseBench.\n\n→ Charts: 13.5% → 55.8% (+42.3) — huge\n → Formatting: 64.2% → 69.4% (+5.2) \n→ Content: 89.7% → 90.3% (+0.6) \n→ Tables: 86.5% → 87.2% (+0.7) \n→ Layout: 16.5% → 14.0% (-2.5) — regressed\n\nReal chart gains, but at ~1.5’/page. Enterprise scale? Not yet.\n\nLlamaParse Agentic: 84.9% overall. ~1.2’/page.\nThe frontier for general document understanding is long. No single model solves it.\n\n→ https://t.co/h7SpuTWYVn",
    "source": "Twitter for iPhone",
    "retweetCount": 8,
    "replyCount": 2,
    "likeCount": 57,
    "quoteCount": 3,
    "viewCount": 19347,
    "createdAt": "Thu Apr 16 21:11:54 +0000 2026",
    "lang": "en",
    "bookmarkCount": 33,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2044886527352647859",
    "displayTextRange": [
      0,
      268
    ],
    "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 πŸ¦™",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": "Business",
      "profilePicture": "https://pbs.twimg.com/profile_images/1967920417760251904/0ytfduMQ_normal.png",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1604278358296055808/1770092126",
      "description": "",
      "location": "",
      "followers": 112070,
      "following": 33,
      "status": "",
      "canDm": false,
      "canMediaTag": true,
      "createdAt": "Sun Dec 18 00:52:44 +0000 2022",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 1532,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 1865,
      "statusesCount": 3827,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "The world's best AI Document OCR\n\nLlamaParse: https://t.co/yQGTiRSNvj\nDocs: https://t.co/us6GCS1Clb",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [
              {
                "display_url": "cloud.llamaindex.ai",
                "expanded_url": "https://cloud.llamaindex.ai/",
                "indices": [
                  46,
                  69
                ],
                "url": "https://t.co/yQGTiRSNvj"
              },
              {
                "display_url": "developers.llamaindex.ai/python/cloud/",
                "expanded_url": "https://developers.llamaindex.ai/python/cloud/",
                "indices": [
                  76,
                  99
                ],
                "url": "https://t.co/us6GCS1Clb"
              }
            ],
            "user_mentions": []
          },
          "url": {
            "urls": [
              {
                "display_url": "llamaindex.ai",
                "expanded_url": "https://www.llamaindex.ai/",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/epzefqQqZx"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "allow_download_status": {
            "allow_download": true
          },
          "display_url": "pic.twitter.com/cyo4QWVsS0",
          "expanded_url": "https://twitter.com/llama_index/status/2044886527352647859/photo/1",
          "ext_media_availability": {
            "status": "Available"
          },
          "features": {
            "large": {
              "faces": []
            },
            "orig": {
              "faces": []
            }
          },
          "id_str": "2044886519324807169",
          "indices": [
            269,
            292
          ],
          "media_key": "3_2044886519324807169",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARxg5XR+VxABCgACHGDldlzWMLMAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHGDldH5XEAEKAAIcYOV2XNYwswAA",
              "media_key": "3_2044886519324807169"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HGDldH5XEAE7Bgb.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 488,
                "w": 871,
                "x": 0,
                "y": 0
              },
              {
                "h": 488,
                "w": 488,
                "x": 0,
                "y": 0
              },
              {
                "h": 488,
                "w": 428,
                "x": 0,
                "y": 0
              },
              {
                "h": 488,
                "w": 244,
                "x": 49,
                "y": 0
              },
              {
                "h": 488,
                "w": 1373,
                "x": 0,
                "y": 0
              }
            ],
            "height": 488,
            "width": 1373
          },
          "sizes": {
            "large": {
              "h": 488,
              "w": 1373
            }
          },
          "type": "photo",
          "url": "https://t.co/cyo4QWVsS0"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [
        {
          "display_url": "github.com/run-llama/Pars…",
          "expanded_url": "http://github.com/run-llama/ParseBench",
          "indices": [
            552,
            575
          ],
          "url": "https://t.co/h7SpuTWYVn"
        }
      ],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}