🐦 Twitter Post Details

Viewing enriched Twitter post

@kaggle

Today, in collaboration with @IBMResearch, we are launching ScarfBench (Self-Contained Application Refactoring Benchmark), an open benchmark designed to test whether coding agents can successfully migrate enterprise Java apps across frameworks like Jakarta EE, Quarkus, and Spring while maintaining the app’s expected behavior. Moving between frameworks takes coordinated changes across dependency injection, persistence, build systems, and deployment infrastructure. An agent can easily generate a migration that looks fine or compiles, only for the app to fail when deployed. ScarfBench puts that to the test. ScarfBench evaluates each model with its harness over 204 migration tasks. Gemini 4 Argon with Antigravity scores 75.2%, followed by Claude Opus 5.5 with Claude Code at 70.5%, and Claude Opus 5 with Claude Code at 69.8%.

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2116307166541860999/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2116307166541860999/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-10-31T01:02:50.314681",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2116307166541860999",
  "url": "https://x.com/kaggle/status/2116307166541860999",
  "twitterUrl": "https://twitter.com/kaggle/status/2116307166541860999",
  "text": "Today, in collaboration with @IBMResearch, we are launching ScarfBench (Self-Contained Application Refactoring Benchmark), an open benchmark designed to test whether coding agents can successfully migrate enterprise Java apps across frameworks like Jakarta EE, Quarkus, and Spring while maintaining the app’s expected behavior.\n\nMoving between frameworks takes coordinated changes across dependency injection, persistence, build systems, and deployment infrastructure. An agent can easily generate a migration that looks fine or compiles, only for the app to fail when deployed. ScarfBench puts that to the test.\n\nScarfBench evaluates each model with its harness over 204 migration tasks. Gemini 4 Argon with Antigravity scores 75.2%, followed by Claude Opus 5.5 with Claude Code at 70.5%, and Claude Opus 5 with Claude Code at 69.8%.",
  "source": "",
  "retweetCount": 2,
  "replyCount": 18,
  "likeCount": 49,
  "quoteCount": 2,
  "viewCount": 4219,
  "createdAt": "Fri Oct 30 23:12:02 +0000 2026",
  "lang": "en",
  "bookmarkCount": 12,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2116307166541860999",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "kaggle",
    "url": "https://x.com/kaggle",
    "twitterUrl": "https://twitter.com/kaggle",
    "id": "80422885",
    "name": "Kaggle",
    "isVerified": false,
    "isBlueVerified": false,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/2110374899281698816/cvMGh-bN_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/80422885/1791993320",
    "description": "",
    "location": "San Francisco",
    "followers": 321539,
    "following": 298,
    "status": "",
    "canDm": false,
    "canMediaTag": false,
    "createdAt": "Tue Oct 06 22:42:08 +0000 2009",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 3276,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1414,
    "statusesCount": 5746,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "The leading platform for crowdsourced benchmarks, competitions, and hackathons where the community shapes real-world progress in AI.",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "kaggle.com",
              "expanded_url": "http://kaggle.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/tvevctHn0D"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null,
    "protected": false
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/WA319ccTU0",
        "expanded_url": "https://x.com/kaggle/status/2116307166541860999/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": [
              {
                "h": 124,
                "w": 124,
                "x": 874,
                "y": 474
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 124,
                "w": 124,
                "x": 874,
                "y": 474
              }
            ]
          }
        },
        "id_str": "2116306729331748864",
        "indices": [
          281,
          304
        ],
        "media_key": "3_2116306729331748864",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR1eocH1lnAACgACHV6iJ8FXUIcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHV6hwfWWcAAKAAIdXqInwVdQhwAA",
            "media_key": "3_2116306729331748864"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HV6hwfWWcAAoJem.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 672,
              "w": 1200,
              "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": 0,
              "y": 0
            },
            {
              "h": 860,
              "w": 1200,
              "x": 0,
              "y": 0
            }
          ],
          "height": 860,
          "width": 1200
        },
        "sizes": {
          "large": {
            "h": 860,
            "w": 1200
          }
        },
        "type": "photo",
        "url": "https://t.co/WA319ccTU0"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "16319797",
        "indices": [
          29,
          41
        ],
        "name": "IBM Research",
        "screen_name": "IBMResearch"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}