@EpochAIResearch
We evaluated Gemini 2.5 Deep Think on FrontierMath. There is no API, so we ran it manually. The results: a new record! We also conducted a more holistic evaluation of its math capabilities. ๐งต https://t.co/NOtVQVGHdV
Viewing enriched Twitter post
We evaluated Gemini 2.5 Deep Think on FrontierMath. There is no API, so we ran it manually. The results: a new record! We also conducted a more holistic evaluation of its math capabilities. ๐งต https://t.co/NOtVQVGHdV
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1976340039178305924/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1976340039178305924/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2025-10-12T13:37:26.103200",
"pipeline_version": "2.0"
} {
"type": "tweet",
"id": "1976340039178305924",
"url": "https://x.com/EpochAIResearch/status/1976340039178305924",
"twitterUrl": "https://twitter.com/EpochAIResearch/status/1976340039178305924",
"text": "We evaluated Gemini 2.5 Deep Think on FrontierMath. There is no API, so we ran it manually. The results: a new record!\n\nWe also conducted a more holistic evaluation of its math capabilities. ๐งต https://t.co/NOtVQVGHdV",
"source": "Twitter for iPhone",
"retweetCount": 94,
"replyCount": 24,
"likeCount": 634,
"quoteCount": 24,
"viewCount": 136123,
"createdAt": "Thu Oct 09 17:32:38 +0000 2025",
"lang": "en",
"bookmarkCount": 114,
"isReply": false,
"inReplyToId": null,
"conversationId": "1976340039178305924",
"displayTextRange": [
0,
192
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "EpochAIResearch",
"url": "https://x.com/EpochAIResearch",
"twitterUrl": "https://twitter.com/EpochAIResearch",
"id": "1529761561170124800",
"name": "Epoch AI",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1866142753127616512/DYcE9bN1_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1529761561170124800/1715099237",
"description": "",
"location": "",
"followers": 28350,
"following": 0,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Thu May 26 09:49:21 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 470,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 504,
"statusesCount": 1589,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1967994675425628526"
],
"profile_bio": {
"description": "Investigating the trajectory of AI for the benefit of society.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "epoch.ai",
"expanded_url": "http://epoch.ai",
"indices": [
0,
23
],
"url": "https://t.co/r5m4cnCNry"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/NOtVQVGHdV",
"expanded_url": "https://twitter.com/EpochAIResearch/status/1976340039178305924/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {},
"orig": {}
},
"id_str": "1976340035797647366",
"indices": [
193,
216
],
"media_key": "3_1976340035797647366",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARttXsqdGgAGCgACG21ey2aawYQAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABG21eyp0aAAYKAAIbbV7LZprBhAAA",
"media_key": "3_1976340035797647366"
}
},
"media_url_https": "https://pbs.twimg.com/media/G21eyp0aAAYN8KB.jpg",
"original_info": {
"focus_rects": [
{
"h": 896,
"w": 1600,
"x": 0,
"y": 0
},
{
"h": 1416,
"w": 1416,
"x": 0,
"y": 0
},
{
"h": 1416,
"w": 1242,
"x": 0,
"y": 0
},
{
"h": 1416,
"w": 708,
"x": 0,
"y": 0
},
{
"h": 1416,
"w": 1600,
"x": 0,
"y": 0
}
],
"height": 1416,
"width": 1600
},
"sizes": {
"large": {
"h": 1416,
"w": 1600
}
},
"type": "photo",
"url": "https://t.co/NOtVQVGHdV"
}
]
},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}