Viewing enriched Twitter post
Wow. Gemini 3.0 on Radiology's Last Exam The first time a general-purpose model has beaten radiology residents with 51% accuracy. Radiology trainees are at 45%. The main significance is that a general model has finally reached a level where it can compete with early-stage human training on a specialized medical exam. Congratulations to @GoogleDeepMind team. @GeminiApp
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1991536165145702808/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1991536165145702808/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2025-11-27T20:44:21.661423",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "1991536165145702808",
"url": "https://x.com/rohanpaul_ai/status/1991536165145702808",
"twitterUrl": "https://twitter.com/rohanpaul_ai/status/1991536165145702808",
"text": "Wow. Gemini 3.0 on Radiology's Last Exam \n\nThe first time a general-purpose model has beaten radiology residents with 51% accuracy.\n\nRadiology trainees are at 45%.\n\nThe main significance is that a general model has finally reached a level where it can compete with early-stage human training on a specialized medical exam.\n\nCongratulations to @GoogleDeepMind team.\n\n@GeminiApp",
"source": "Twitter for iPhone",
"retweetCount": 211,
"replyCount": 52,
"likeCount": 1759,
"quoteCount": 30,
"viewCount": 231132,
"createdAt": "Thu Nov 20 15:56:37 +0000 2025",
"lang": "en",
"bookmarkCount": 391,
"isReply": false,
"inReplyToId": null,
"conversationId": "1991536165145702808",
"displayTextRange": [
0,
277
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "rohanpaul_ai",
"url": "https://x.com/rohanpaul_ai",
"twitterUrl": "https://twitter.com/rohanpaul_ai",
"id": "2588345408",
"name": "Rohan Paul",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1816185267037859840/Fd18CH0v_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/2588345408/1729559315",
"description": "",
"location": "Ex Inv Banking (Deutsche)",
"followers": 111987,
"following": 8366,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Wed Jun 25 22:38:54 +0000 2014",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 53748,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 24491,
"statusesCount": 60754,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1965551636082032917"
],
"profile_bio": {
"description": "Compiling in real-time, the race towards AGI.\n\nThe Largest Show on X for AI.\n\n🗞️ Get my daily AI analysis newsletter to your email 👉 https://t.co/6LBxO8215l",
"entities": {
"description": {
"urls": [
{
"display_url": "rohan-paul.com",
"expanded_url": "https://www.rohan-paul.com",
"indices": [
134,
157
],
"url": "https://t.co/6LBxO8215l"
}
]
},
"url": {
"urls": [
{
"display_url": "rohan-paul.com",
"expanded_url": "http://www.rohan-paul.com",
"indices": [
0,
23
],
"url": "https://t.co/2NKnK0wIil"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/zyDUYHalu0",
"expanded_url": "https://twitter.com/rohanpaul_ai/status/1991536165145702808/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {},
"orig": {}
},
"id_str": "1991535370660696065",
"indices": [
278,
301
],
"media_key": "3_1991535370660696065",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARujWt4121ABCgACG6NblzDacZgAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABG6Na3jXbUAEKAAIbo1uXMNpxmAAA",
"media_key": "3_1991535370660696065"
}
},
"media_url_https": "https://pbs.twimg.com/media/G6Na3jXbUAE8Uff.jpg",
"original_info": {
"focus_rects": [
{
"h": 1120,
"w": 2000,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 1358,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 1191,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 679,
"x": 11,
"y": 0
},
{
"h": 1358,
"w": 2000,
"x": 0,
"y": 0
}
],
"height": 1358,
"width": 2000
},
"sizes": {
"large": {
"h": 1358,
"w": 2000
}
},
"type": "photo",
"url": "https://t.co/zyDUYHalu0"
}
]
},
"card": null,
"place": {},
"entities": {
"user_mentions": [
{
"id_str": "4783690002",
"indices": [
343,
358
],
"name": "Google DeepMind",
"screen_name": "GoogleDeepMind"
},
{
"id_str": "1806359170830172162",
"indices": [
366,
376
],
"name": "G3mini",
"screen_name": "GeminiApp"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "1991378471604334604",
"url": "https://x.com/DrDatta_AIIMS/status/1991378471604334604",
"twitterUrl": "https://twitter.com/DrDatta_AIIMS/status/1991378471604334604",
"text": "🔥 Gemini 3.0 vs Radiologists: RadLE Benchmark Results Are OUT! \n\n☠️ Is it game over for Radiology? Let us find out! ⬇️\n\n🫨 Since yesterday, Gemini 3.0 has been everywhere for crushing benchmarks. My inbox exploded asking: “But how did it do on the hardest visual reasoning benchmark in healthcare?”\n\nSo we ran it!\nAnd here you go. 👇\n\n➡️ Gemini 3.0 Pro on RadLE v1:\n\n✅ 51% accuracy; first time a general-purpose model has beaten radiology residents\n✅ Radiology residents: 45%\n✅ Board-certified radiologists: ~83%\n✅ Shows clean step-by-step reasoning in some tough cases (appendix localization, mimics ruled out, etc.)\n\n🚀 This is the first time ever that a generalist model has crossed the trainee bar on RadLE v1! \n\nCongratulations to @GoogleDeepMind and @Google team including @vivnat, @alan_karthi and all others for cooking this time! \n\nFull breakdown here:\n\n🔗 Link in comments / bio\n\n🔥 Huge shoutout to Lakshmi, Divya, Upasana, Hakikat, Kautik & the entire #CRASHLab team at @KCDH_A for turning around in under a day. \n\n🙌 If you are a medical AI lab and want to improve your performances and want our expert insights, reach out!",
"source": "Twitter for iPhone",
"retweetCount": 199,
"replyCount": 76,
"likeCount": 1232,
"quoteCount": 68,
"viewCount": 516071,
"createdAt": "Thu Nov 20 05:30:00 +0000 2025",
"lang": "en",
"bookmarkCount": 492,
"isReply": false,
"inReplyToId": null,
"conversationId": "1991378471604334604",
"displayTextRange": [
0,
272
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "DrDatta_AIIMS",
"url": "https://x.com/DrDatta_AIIMS",
"twitterUrl": "https://twitter.com/DrDatta_AIIMS",
"id": "1332378558711304193",
"name": "Dr. Datta M.D. (AIIMS Delhi)",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1876237030562451456/8sK-0bBQ_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1332378558711304193/1620594676",
"description": "",
"location": "DEL/KOL/BOM/PUNE/HYD/PY/BLR",
"followers": 29341,
"following": 2843,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Fri Nov 27 17:39:48 +0000 2020",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 31819,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1438,
"statusesCount": 10950,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1980606329380327647"
],
"profile_bio": {
"description": "Radiologist ➡️ All things AI\n\nBuilding #CRASHLab @ashokauniv @kcdh_a\n\nEvals, Foundational Models and Autonomous Agents\n\nLikes, RTs: My Views\n\n💩 posts often!",
"entities": {
"description": {
"hashtags": [
{
"indices": [
39,
48
],
"text": "CRASHLab"
}
],
"user_mentions": [
{
"id_str": "0",
"indices": [
49,
60
],
"name": "",
"screen_name": "ashokauniv"
},
{
"id_str": "0",
"indices": [
61,
68
],
"name": "",
"screen_name": "kcdh_a"
}
]
},
"url": {
"urls": [
{
"display_url": "drdattaaiims.github.io",
"expanded_url": "https://drdattaaiims.github.io/",
"indices": [
0,
23
],
"url": "https://t.co/btMgISLdrn"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/WuSx2Doimw",
"expanded_url": "https://twitter.com/DrDatta_AIIMS/status/1991378471604334604/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {},
"orig": {}
},
"id_str": "1991261283736514563",
"indices": [
273,
296
],
"media_key": "3_1991261283736514563",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARuiYZZgGnADCgACG6LMK01WMAwAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABG6JhlmAacAMKAAIboswrTVYwDAAA",
"media_key": "3_1991261283736514563"
}
},
"media_url_https": "https://pbs.twimg.com/media/G6JhlmAacAM7iYf.jpg",
"original_info": {
"focus_rects": [
{
"h": 1120,
"w": 2000,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 1358,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 1191,
"x": 0,
"y": 0
},
{
"h": 1358,
"w": 679,
"x": 11,
"y": 0
},
{
"h": 1358,
"w": 2000,
"x": 0,
"y": 0
}
],
"height": 1358,
"width": 2000
},
"sizes": {
"large": {
"h": 1358,
"w": 2000
}
},
"type": "photo",
"url": "https://t.co/WuSx2Doimw"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [
{
"indices": [
959,
968
],
"text": "CRASHLab"
}
],
"user_mentions": [
{
"id_str": "4783690002",
"indices": [
733,
748
],
"name": "Google DeepMind",
"screen_name": "GoogleDeepMind"
},
{
"id_str": "20536157",
"indices": [
753,
760
],
"name": "Google",
"screen_name": "Google"
},
{
"id_str": "97205267",
"indices": [
776,
783
],
"name": "Vivek Natarajan",
"screen_name": "vivnat"
},
{
"id_str": "1020053469787566082",
"indices": [
785,
797
],
"name": "Alan Karthikesalingam",
"screen_name": "alan_karthi"
},
{
"id_str": "1689891412542885889",
"indices": [
977,
984
],
"name": "Koita Centre for Digital Health - Ashoka (KCDH-A)",
"screen_name": "KCDH_A"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}