@Teknium1
RT @NousResearch: Measuring Thinking Efficiency in Reasoning Models: The Missing Benchmark https://t.co/b1e1rJx6vZ We measured token usag…
🐦 Twitter Post Details
Viewing enriched Twitter post
📊 Media Metadata
{
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1956144728677998790/media_0.png?",
"filename": "media_0.png"
}
],
"processed_at": "2025-08-15T08:15:59.055379",
"pipeline_version": "2.0"
}🔧 Raw API Response
{
"type": "tweet",
"id": "1956144728677998790",
"url": "https://x.com/Teknium1/status/1956144728677998790",
"twitterUrl": "https://twitter.com/Teknium1/status/1956144728677998790",
"text": "RT @NousResearch: Measuring Thinking Efficiency in Reasoning Models: The Missing Benchmark\n\nhttps://t.co/b1e1rJx6vZ\n\nWe measured token usag…",
"source": "Twitter for iPhone",
"retweetCount": 45,
"replyCount": 14,
"likeCount": 322,
"quoteCount": 11,
"viewCount": 31166,
"createdAt": "Fri Aug 15 00:03:41 +0000 2025",
"lang": "en",
"bookmarkCount": 94,
"isReply": false,
"inReplyToId": null,
"conversationId": "1956144728677998790",
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "Teknium1",
"url": "https://x.com/Teknium1",
"twitterUrl": "https://twitter.com/Teknium1",
"id": "1365020011123773442",
"name": "Teknium (e/λ)",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1642401912648777728/2KFikPsE_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1365020011123773442/1679544051",
"description": "",
"location": "USA",
"followers": 49430,
"following": 4453,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Thu Feb 25 19:25:11 +0000 2021",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 107350,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 2645,
"statusesCount": 42569,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {
"label": {
"badge": {
"url": "https://pbs.twimg.com/profile_images/1816254738234761216/TX7TW-Mp_bigger.jpg"
},
"description": "Nous Research",
"url": {
"url": "https://twitter.com/NousResearch",
"url_type": "DeepLink"
},
"user_label_type": "BusinessLabel",
"user_label_display_type": "Badge"
}
},
"possiblySensitive": false,
"pinnedTweetIds": [
"1900220169412341993"
],
"profile_bio": {
"description": "Cofounder and Head of Post Training @NousResearch, prev @StabilityAI\nGithub: https://t.co/LZwHTUFwPq\nHuggingFace: https://t.co/sN2FFU8PVE",
"entities": {
"description": {
"urls": [
{
"display_url": "github.com/teknium1",
"expanded_url": "http://github.com/teknium1",
"indices": [
77,
100
],
"url": "https://t.co/LZwHTUFwPq"
},
{
"display_url": "huggingface.co/teknium",
"expanded_url": "http://huggingface.co/teknium",
"indices": [
114,
137
],
"url": "https://t.co/sN2FFU8PVE"
}
],
"user_mentions": [
{
"id_str": "0",
"indices": [
36,
49
],
"name": "",
"screen_name": "NousResearch"
},
{
"id_str": "0",
"indices": [
56,
68
],
"name": "",
"screen_name": "StabilityAI"
}
]
},
"url": {
"urls": [
{
"display_url": "github.com/sponsors/tekni…",
"expanded_url": "http://github.com/sponsors/teknium1",
"indices": [
0,
23
],
"url": "https://t.co/7DnNfZEOPh"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "nousresearch.com/measuring-thin…",
"expanded_url": "https://nousresearch.com/measuring-thinking-efficiency-in-reasoning-models-the-missing-benchmark/",
"indices": [
92,
115
],
"url": "https://t.co/b1e1rJx6vZ"
}
],
"user_mentions": [
{
"id_str": "1318419526132862976",
"indices": [
3,
16
],
"name": "Nous Research",
"screen_name": "NousResearch"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": {
"type": "tweet",
"id": "1956090990005248341",
"url": "https://x.com/NousResearch/status/1956090990005248341",
"twitterUrl": "https://twitter.com/NousResearch/status/1956090990005248341",
"text": "Measuring Thinking Efficiency in Reasoning Models: The Missing Benchmark\n\nhttps://t.co/ih1cYgeYOw\n\nWe measured token usage across reasoning models: open models output 1.5-4x more tokens than closed models on identical tasks, but with huge variance depending on task type (up to 10x on simple questions).\n\nThis hidden cost often negates per-token pricing advantages. Token efficiency should become a primary target alongside accuracy benchmarks, especially considering non-reasoning use cases.\n\nRead the thorough review of reasoning efficiency across the open and closed model landscape in our latest blog post in collaboration with our researcher in residence, Tim. \n\nSee more of their work here: https://t.co/ieOzjJc06o",
"source": "Twitter for iPhone",
"retweetCount": 45,
"replyCount": 14,
"likeCount": 322,
"quoteCount": 11,
"viewCount": 31166,
"createdAt": "Thu Aug 14 20:30:09 +0000 2025",
"lang": "en",
"bookmarkCount": 94,
"isReply": false,
"inReplyToId": null,
"conversationId": "1956090990005248341",
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "NousResearch",
"url": "https://x.com/NousResearch",
"twitterUrl": "https://twitter.com/NousResearch",
"id": "1318419526132862976",
"name": "Nous Research",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": "Business",
"profilePicture": "https://pbs.twimg.com/profile_images/1816254738234761216/TX7TW-Mp_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1318419526132862976/1698625831",
"description": "",
"location": "New York",
"followers": 79951,
"following": 69,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Oct 20 05:11:31 +0000 2020",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 2906,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 127,
"statusesCount": 624,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1922744483571171605"
],
"profile_bio": {
"description": "The AI Accelerator Company\nhttps://t.co/vrD0aDIGDQ",
"entities": {
"description": {
"urls": [
{
"display_url": "discord.gg/nousresearch",
"expanded_url": "https://discord.gg/nousresearch",
"indices": [
27,
50
],
"url": "https://t.co/vrD0aDIGDQ"
}
]
},
"url": {
"urls": [
{
"display_url": "nousresearch.com",
"expanded_url": "http://nousresearch.com",
"indices": [
0,
23
],
"url": "https://t.co/bHRc162fj7"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/LY1083won8",
"expanded_url": "https://twitter.com/NousResearch/status/1956090990005248341/photo/1",
"ext_media_availability": {
"status": "Available"
},
"features": {
"large": {},
"orig": {}
},
"id_str": "1956090774321553410",
"indices": [
279,
302
],
"media_key": "3_1956090774321553410",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARslbjIH2uACCgACGyVuZD+a4VUAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABGyVuMgfa4AIKAAIbJW5kP5rhVQAA",
"media_key": "3_1956090774321553410"
}
},
"media_url_https": "https://pbs.twimg.com/media/GyVuMgfa4AIYlsO.jpg",
"original_info": {
"focus_rects": [
{
"h": 630,
"w": 1125,
"x": 75,
"y": 0
},
{
"h": 630,
"w": 630,
"x": 570,
"y": 0
},
{
"h": 630,
"w": 553,
"x": 647,
"y": 0
},
{
"h": 630,
"w": 315,
"x": 885,
"y": 0
},
{
"h": 630,
"w": 1200,
"x": 0,
"y": 0
}
],
"height": 630,
"width": 1200
},
"sizes": {
"large": {
"h": 630,
"w": 1200
}
},
"type": "photo",
"url": "https://t.co/LY1083won8"
}
]
},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "nousresearch.com/measuring-thin…",
"expanded_url": "https://nousresearch.com/measuring-thinking-efficiency-in-reasoning-models-the-missing-benchmark/",
"indices": [
74,
97
],
"url": "https://t.co/ih1cYgeYOw"
},
{
"display_url": "github.com/cpldcpu/",
"expanded_url": "https://github.com/cpldcpu/",
"indices": [
697,
720
],
"url": "https://t.co/ieOzjJc06o"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
},
"article": null
}