Aleksei Dorkin PRO

adorkin's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset about 1 hour ago

scthornton/securecode-v2.1

Preview • Updated about 18 hours ago • 9 • 3

liked a dataset 1 day ago

tencent/CL-bench

Viewer • Updated 1 day ago • 1.9k • 682 • 78

upvoted an article 1 day ago

view article

Article

Community Evals: Because we're done trusting black-box leaderboards over the community

• 
• 
• +5

4 days ago

•

39

commented on 🇵🇭 FilBench - Can LLMs Understand and Generate Filipino? 1 day ago

view reply

Just a heads-up in case any of the maintainers see this, the embedded Gradio space at the top of the article seems to be broken.

upvoted an article 1 day ago

view article

Article

🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?

• 
• 
• +7

Aug 12, 2025

•

23

upvoted a changelog 1 day ago

view changelog

Changelog

Community Evals and Benchmark Repositories

2 days ago

• 28

New activity in OpenEvals/README 1 day ago

New Benchmark Dataset

🚀 1

1

#2 opened 9 days ago by

burtenshaw

upvoted a collection 2 days ago

Instruction Pretrained Experiments

Collection

Experiments associated with the paper 'Continued Pretraining and Interpretability-Based Evaluation for Low-Resource Languages: A Galician Case Study' • 3 items • Updated Dec 11, 2025 • 1

liked a model 3 days ago

Qwen/Qwen3-Coder-Next

Text Generation • 80B • Updated 4 days ago • 53.5k • • 576

liked a dataset 3 days ago

HiTZ/TOOLtifruti

Updated 3 days ago • 15 • 1

upvoted a paper 5 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published 8 days ago • 82

liked a dataset 6 days ago

uv-scripts/vllm

Updated 6 days ago • 367 • 10

upvoted 3 collections 7 days ago

Open Coding Agents

Collection

11 items • Updated 5 days ago • 44

MMFineReason

Collection

High-quality STEM reasoning dataset for Multimodal LLM post-training. • 14 items • Updated 4 days ago • 20

Continually pre-trained models

Collection

Language-specific LLMs continually pre-trained from fully open English base models • 2 items • Updated 17 days ago • 1

liked a dataset 7 days ago

Qwen/DeepPlanning

Viewer • Updated 12 days ago • 2.14k • 655 • 161

liked 2 datasets 8 days ago

sentence-transformers/askubuntu-questions

Viewer • Updated 8 days ago • 168k • 46 • 1

sentence-transformers/askubuntu

Viewer • Updated 8 days ago • 13.1k • 53 • 1

upvoted a changelog 8 days ago

view changelog

Changelog

View Running Jobs Count from the User Menu

9 days ago

• 41

upvoted a collection 9 days ago

MS MARCO Mined Triplets

Collection

These datasets contain MS MARCO Triplets gathered by mining hard negatives using various models. Each dataset has various subsets. • 16 items • Updated 9 days ago • 13