Hi,

Niels here from the open-source team at Hugging Face. Like many others, I was a huge fan of paperswithcode. Sadly, that website is no longer maintained after its acquisition by Meta.

Hence, I've been working on reviving it. I obviously use AI agents to parse papers at scale and automatically generate leaderboards (for now I'm the one verifying results). So far, I've only parsed high-impact papers for which I know they're SOTA, like Qwen 3.5 and 3.6, RF-DETR for object detection, DINOv3, SOTA embedding models from the MTEB leaderboard, the Open ASR Leaderboard for automatic speech recognition models, etc.

For now, it includes the following:

• trending papers by default based on Github star velocity
• categorization by domain, e.g., OCR
• methods, which PwC used to have, e.g., RLVR
• eval results for high-impact papers, see e.g., Qwen 3.5 at the bottom
• leaderboards for each domain, e.g., MMTEB or COCO val 2017
• support for citation counts (you can also see the most cited papers by domain!)
• automated linked Github, project page URLs, and artifacts (+ multiple repos are supported on a paper page)
• support for external papers beyond Arxiv, see e.g., DeepSeek v4
• Harness reports for coding agent benchmarks, e.g., Terminal Bench
• "Sign in with HF" and Storage Buckets are used to store humbnails, paper PDFs, and overall data backups.

I'm curious about your feedback + feature requests!

Try it at paperswithcode.co

https://preview.redd.it/whwji560fw1h1.png?width=3452&format=png&auto=webp&s=55bb7a30c1be58d140f7efcb07a31c6dac5693c7

See e.g. the SOTA leaderboard for Terminal Bench 2.0:

https://preview.redd.it/98w9pi89fw1h1.png?width=3456&format=png&auto=webp&s=408fb64b0ba85ba24f55daa81d547d7c68e73951

A paper page looks like this: https://paperswithcode.co/paper/2602.15763

https://preview.redd.it/fiizit6dfw1h1.png?width=3450&format=png&auto=webp&s=9ea05a77ca5583a2fb395dccc95ba52c433362c5

Apparently the study was only done in 20 people but it's still encouraging.

Abstract

Metabolic disorders have been recognized as a major contributor to the occurrence and progression of osteoarthritis (OA). Identifying novel therapeutic agents to ameliorate the progression of OA with metabolic disorder is crucial. In this study, we demonstrate that ... a glucagon-like peptide-1 receptor (GLP-1R) agonist, exhibits strong chondroprotective effects in an OA mouse model with obesity, as evidenced by reduced pathological changes, including cartilage degeneration, osteophyte formation, synovial lesion, and pain sensitivity. A randomized pilot clinical study (ChiCTR2200066291) further supports these findings. By designing a precise diet-controlled setting to rule out the effect of appetite suppression and weight loss induced by SG, we demonstrate a weight loss-independent mechanism. Through regulating the "GLP-1R-AMPK-PFKFB3" axis, the SG reprograms chondrocyte metabolism profile from glycolysis to oxidative phosphorylation under inflammatory conditions, resulting in cartilage restoration.