@HuggingPapers
SWE-bench Science A new benchmark for scientific software engineering: 119 tasks across 98 repositories and 20 domains. Even the best agent, Claude Code with Opus-5, achieves under 50% pass@1. https://t.co/LtdNeJdwEh
Viewing enriched Twitter post
SWE-bench Science A new benchmark for scientific software engineering: 119 tasks across 98 repositories and 20 domains. Even the best agent, Claude Code with Opus-5, achieves under 50% pass@1. https://t.co/LtdNeJdwEh
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2090773411039457342/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2090773411039457342/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-08-21T14:01:56.031986",
"pipeline_version": "2.0"
} {
"type": "tweet",
"id": "2090773411039457342",
"url": "https://x.com/HuggingPapers/status/2090773411039457342",
"twitterUrl": "https://twitter.com/HuggingPapers/status/2090773411039457342",
"text": "SWE-bench Science\n\nA new benchmark for scientific software engineering: 119 tasks across 98 repositories and 20 domains. Even the best agent, Claude Code with Opus-5, achieves under 50% pass@1. https://t.co/LtdNeJdwEh",
"source": "Twitter for iPhone",
"retweetCount": 2,
"replyCount": 2,
"likeCount": 19,
"quoteCount": 0,
"viewCount": 2180,
"createdAt": "Fri Aug 21 12:10:00 +0000 2026",
"lang": "en",
"bookmarkCount": 6,
"isReply": false,
"inReplyToId": null,
"conversationId": "2090773411039457342",
"displayTextRange": [
0,
193
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "HuggingPapers",
"url": "https://x.com/HuggingPapers",
"twitterUrl": "https://twitter.com/HuggingPapers",
"id": "1906617820122595328",
"name": "DailyPapers",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1906618607368273920/09C2Z22U_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1906617820122595328/1743408239",
"description": "",
"location": "Anywhere",
"followers": 20535,
"following": 4,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Mon Mar 31 08:01:39 +0000 2025",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 50,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 3106,
"statusesCount": 6754,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "Tweeting interesting papers submitted at https://t.co/rXX8x0HzXV.\n\nSubmit your own at https://t.co/QhbJKXBd4Q, and link models/datasets/demos to it!",
"entities": {
"description": {
"urls": [
{
"display_url": "huggingface.co/papers",
"expanded_url": "http://huggingface.co/papers",
"indices": [
41,
64
],
"url": "https://t.co/rXX8x0HzXV"
},
{
"display_url": "hf.co/papers/submit",
"expanded_url": "http://hf.co/papers/submit",
"indices": [
86,
109
],
"url": "https://t.co/QhbJKXBd4Q"
}
]
},
"url": {
"urls": [
{
"display_url": "huggingface.co/docs/hub/en/mo…",
"expanded_url": "https://huggingface.co/docs/hub/en/model-release-checklist",
"indices": [
0,
23
],
"url": "https://t.co/rEWlTAkfrC"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.x.com/LtdNeJdwEh",
"expanded_url": "https://x.com/HuggingPapers/status/2090773411039457342/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": []
},
"orig": {
"faces": []
}
},
"id_str": "2090773404353798144",
"indices": [
194,
217
],
"media_key": "3_2090773404353798144",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR0D61V4V6AACgACHQPrVwbWsD4AAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHQPrVXhXoAAKAAIdA+tXBtawPgAA",
"media_key": "3_2090773404353798144"
}
},
"media_url_https": "https://pbs.twimg.com/media/HQPrVXhXoAAsSHf.jpg",
"original_info": {
"focus_rects": [
{
"h": 907,
"w": 1620,
"x": 0,
"y": 0
},
{
"h": 907,
"w": 907,
"x": 283,
"y": 0
},
{
"h": 907,
"w": 796,
"x": 338,
"y": 0
},
{
"h": 907,
"w": 454,
"x": 509,
"y": 0
},
{
"h": 907,
"w": 1734,
"x": 0,
"y": 0
}
],
"height": 907,
"width": 1734
},
"sizes": {
"large": {
"h": 907,
"w": 1734
}
},
"type": "photo",
"url": "https://t.co/LtdNeJdwEh"
}
]
},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}