datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sdxl-models
Aisha-AI.com 💜
A NSFW Social Network powered by AI Characters
The models saved in this dataset are currently being used, or have been used at some point, to generate images and videos.
The dataset is public and can be used as a backup or alternative to more unstable servers (like the unfortunate Civitai).
ai-model-popularity
Datamata AI Model Popularity Index
Weekly popularity of the most-downloaded and trending Hugging Face models: trailing downloads, likes, the model's task and its trending rank. One row per model from the most recent weekly snapshot.
Latest snapshot: 2026-09-20
Models in this release: 50
Updated: weekly
Licence: CC BY 4.0 — free to use and adapt, including commercially, with attribution.
Source & methodology: https://www.datamatastudios.com/datasets
Quickstart… See the full description on the dataset page: https://huggingface.co/datasets/datamatastudios/ai-model-popularity.civit-ai-modelsrvc-modelsCheck out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
flux-2-klein-modelsflux-dev-modelsphyground
PhyGround: Benchmarking Physical Reasoning in Generative World Models
Project page ·
Paper ·
Evaluation code ·
PhyJudge-9B
PhyGround is a criteria-grounded benchmark for diagnosing physical failures in
generated video. It contains 250 prompts covering 13 observable physical
laws across solid-body mechanics, fluid dynamics, and optics. Each prompt is
paired with a first-frame image, 10 released generation configurations, and
applicable-law labels.
The Hub repository includes:… See the full description on the dataset page: https://huggingface.co/datasets/NU-World-Model-Embodied-AI/phyground.aimodelpaintingaimodelsAll of my models posted on AI HUB
ai-model-pricing-daily
AI Model Pricing Daily
A daily snapshot of AI model pricing and metadata — flagship and open models across
providers (OpenAI, Anthropic, Google, Mistral, Groq, ...) — exported through
Dynamic Feed, a live, verifiable data API whose every response
is Ed25519-signed. One file per day (data/YYYY-MM-DD.jsonl), one JSON object per
model per line. Because model prices change without notice and post-date every model's
training cutoff, a dated, signed daily series is the form this data… See the full description on the dataset page: https://huggingface.co/datasets/dynamicfeed/ai-model-pricing-daily.details_AI-Sweden-Models__gpt-sw3-6.7b-v2-instruct
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-6.7b-v2-instruct.details_AI-Sweden-Models__gpt-sw3-40b
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-40b
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-40b on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-40b.foundation-models-perturbationData for the paper "Foundation Models Improve Perturbation Response Prediction" as described on GitHub.
details_AI-Sweden-Models__gpt-sw3-20b
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-20b
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-20b on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-20b.details_AI-Sweden-Models__gpt-sw3-6.7b-v2
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-6.7b-v2
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-6.7b-v2 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-6.7b-v2.details_AI-Sweden-Models__gpt-sw3-20b-instruct
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-20b-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-20b-instruct on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-20b-instruct.details_AI-Sweden-Models__gpt-sw3-1.3b-instruct
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-1.3b-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-1.3b-instruct on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-1.3b-instruct.details_AI-Sweden-Models__gpt-sw3-6.7b
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-6.7b
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-6.7b on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-6.7b.aimodel
cf_ai_intelligent-assistant
AI chat assistant built on Cloudflare's platform using Llama 3.3, with conversation memory powered by Durable Objects.
Live Demo
Chat UI: https://cf-ai-assistant-76b.pages.dev
What it does
This is a chat application where you can have conversations with Llama 3.3. The conversations are saved using Cloudflare Durable Objects, so when you refresh the page your chat history is still there. Everything runs on Cloudflare's… See the full description on the dataset page: https://huggingface.co/datasets/cheumk/aimodel.details_AI-Sweden-Models__gpt-sw3-1.3b
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-1.3b
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-1.3b on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-1.3b.modelsai-models-2026
AI Models & Releases 2026
AI model releases, benchmarks, capabilities. Updated daily via automated collection pipeline.
Part of the Legion Data Factory — historical AI ecosystem datasets 2026.
Methodology
Automated collection from public sources (HackerNews, RSS feeds, APIs).
Updated daily via cron job. Raw data, minimal processing.
License
CC BY 4.0
🔑 API Access — Updated Daily
Live data via Legion AI API | Documentation
Free: 100… See the full description on the dataset page: https://huggingface.co/datasets/gemmozero/ai-models-2026.details_AI-Sweden-Models__gpt-sw3-126m
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-126m
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-126m on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-126m.details_AI-Sweden-Models__gpt-sw3-126m-instruct
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-126m-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-126m-instruct on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-126m-instruct.details_AI-Sweden-Models__gpt-sw3-356m-instruct
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-356m-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-356m-instruct on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-356m-instruct.details_AI-Sweden-Models__gpt-sw3-356m
Dataset Card for Evaluation run of AI-Sweden-Models/gpt-sw3-356m
Dataset Summary
Dataset automatically created during the evaluation run of model AI-Sweden-Models/gpt-sw3-356m on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_AI-Sweden-Models__gpt-sw3-356m.BiaSWE
About BiaSWE
We present BiaSWE, a small annotated dataset for misogyny detection in Swedish, annotated for hate speech, misogyny, misogyny type categories and severity by a group of experts in social sciences and humanities. This dataset is a proof of concept and it can be used to perform classification of misogynistic vs non-misogynistic text, as well as debiasing on Language Models.
Content warning: Sensitive content might appear in this dataset. The language does not reflect the… See the full description on the dataset page: https://huggingface.co/datasets/AI-Sweden-Models/BiaSWE.New_models_runsTB2_model_gpt_5.5_Opus_4.8Micro-Model-Bench
Micro-Model-Bench
Micro-Model-Bench is a collection of benchmark results that have been collected using lm-evaluation-harness
Models Recorded
2026-08-27:
154 model records across 49 organizations
125 records marked isValid: true, all other models haven't been evaluated because of gated access or lm-eval not being able to benchmark them.
What benchmarks are included:
ARC-Easy: arc_easy_acc, arc_easy_acc_norm
ARC-Challenge: arc_challenge_acc… See the full description on the dataset page: https://huggingface.co/datasets/veyra-ai/Micro-Model-Bench.