🐦 Twitter Post Details

Viewing enriched Twitter post

@jerryjliu0

We benchmarked GPT-5.5 on document understanding šŸ“„šŸ“Š We ran it through ParseBench, our comprehensive OCR benchmark over enterprise documents. We evaluated metrics across various dimensions: visual grounding, tables, charts, and more. We evaluated GPT-5.5 on mid thinking and zero-thinking modes. When compared against GPT-5.4 (0 thinking) and Opus 4.7 (adaptive thinking): šŸ“ˆ GPT-5.5 wins on tables šŸ“ˆ GPT-5.5 wins on visual grounding šŸ“‰ GPT-5.5 0-thinking does worse on charts than GPT-5.4 0-thinking šŸ“‰ Higher thinking does worse than lower thinking of content faithfulness, semantic formatting šŸ“‰ Opus 4.7 wins overall on content faithfulness and semantic formatting šŸ’ø GPT-5.5 is expensive: 13c per page at mid-thinking modes and 5.93 at 0-thinking! This is 5x the cost of any competitive OCR solution. Conclusion: GPT-5.5 is one of the better frontier models out there in terms of pure accuracy, but def not pound for pound w.r.t price.

Media 1

šŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2047803921037656389/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2047803921037656389/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-05-11T22:57:30.517041",
  "pipeline_version": "2.0"
}

šŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2047803921037656389",
  "url": "https://x.com/jerryjliu0/status/2047803921037656389",
  "twitterUrl": "https://twitter.com/jerryjliu0/status/2047803921037656389",
  "text": "We benchmarked GPT-5.5 on document understanding šŸ“„šŸ“Š\n\nWe ran it through ParseBench, our comprehensive OCR benchmark over enterprise documents. We evaluated metrics across various dimensions: visual grounding, tables, charts, and more.\n\nWe evaluated GPT-5.5 on mid thinking and zero-thinking modes. When compared against GPT-5.4 (0 thinking) and Opus 4.7 (adaptive thinking):\nšŸ“ˆ GPT-5.5 wins on tables\nšŸ“ˆ GPT-5.5 wins on visual grounding\nšŸ“‰ GPT-5.5 0-thinking does worse on charts than GPT-5.4 0-thinking\nšŸ“‰ Higher thinking does worse than lower thinking of content faithfulness, semantic formatting\nšŸ“‰ Opus 4.7 wins overall on content faithfulness and semantic formatting\nšŸ’ø GPT-5.5 is expensive: 13c per page at mid-thinking modes and 5.93 at 0-thinking! This is 5x the cost of any competitive OCR solution.\n\nConclusion: GPT-5.5 is one of the better frontier models out there in terms of pure accuracy, but def not pound for pound w.r.t price.",
  "source": "Twitter for iPhone",
  "retweetCount": 17,
  "replyCount": 11,
  "likeCount": 178,
  "quoteCount": 4,
  "viewCount": 23459,
  "createdAt": "Fri Apr 24 22:24:35 +0000 2026",
  "lang": "en",
  "bookmarkCount": 61,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2047803921037656389",
  "displayTextRange": [
    0,
    275
  ],
  "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": "Parsing the world's hardest PDFs @llama_index. cofounder/CEO\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
    "location": "",
    "followers": 74145,
    "following": 1475,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed Sep 07 22:54:31 +0000 2011",
    "entities": {
      "description": {
        "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"
          }
        ]
      },
      "url": {
        "urls": [
          {
            "display_url": "llamaindex.ai",
            "expanded_url": "https://www.llamaindex.ai/",
            "indices": [
              0,
              23
            ],
            "url": "https://t.co/YiIfjVlzb6"
          }
        ]
      }
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8726,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1508,
    "statusesCount": 6942,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {},
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/mNPo2Zf6uI",
        "expanded_url": "https://x.com/jerryjliu0/status/2047803921037656389/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "medium": {
            "faces": []
          },
          "orig": {
            "faces": []
          },
          "small": {
            "faces": []
          }
        },
        "id_str": "2047803541369356288",
        "indices": [
          276,
          299
        ],
        "media_key": "3_2047803541369356288",
        "media_results": {
          "result": {
            "media_key": "3_2047803541369356288"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HGtCeJ0bgAAPIU-.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 860,
              "w": 1536,
              "x": 0,
              "y": 0
            },
            {
              "h": 860,
              "w": 860,
              "x": 0,
              "y": 0
            },
            {
              "h": 860,
              "w": 754,
              "x": 0,
              "y": 0
            },
            {
              "h": 860,
              "w": 430,
              "x": 155,
              "y": 0
            },
            {
              "h": 860,
              "w": 2124,
              "x": 0,
              "y": 0
            }
          ],
          "height": 860,
          "width": 2124
        },
        "sizes": {
          "large": {
            "h": 829,
            "resize": "fit",
            "w": 2048
          },
          "medium": {
            "h": 486,
            "resize": "fit",
            "w": 1200
          },
          "small": {
            "h": 275,
            "resize": "fit",
            "w": 680
          },
          "thumb": {
            "h": 150,
            "resize": "crop",
            "w": 150
          }
        },
        "type": "photo",
        "url": "https://t.co/mNPo2Zf6uI"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "article": null
}