Kaggle
@kaggle
Followers
309K
Following
3K
Media
1K
Statuses
5K
Kaggle is the largest global AI community of developers, researchers, and enthusiasts who compete, collaborate, and benchmark what's next in AI.
San Francisco
Joined October 2009
Key highlights: - 900 challenging search questions structured as “causal chains” - Prompts across 17 fields - Verifiable scoring to compare models
0
2
2
🚀 New on Kaggle Benchmarks: DeepSearchQA developed by @googledeepmind! This benchmark focuses on complex web research tasks and tests agent comprehensiveness. Check the leaderboard: https://t.co/ofQiXBr1P1
4
10
79
We evaluated 15 leading models. Gemini 3 Pro achieved the top score of 68.8%. While search and internal knowledge has improved, multimodal factuality remains an industry-wide challenge. We’re sharing these benchmarks on @kaggle to help the research community build more reliable
deepmind.google
The FACTS Benchmark Suite provides a systematic evaluation of Large Language Models (LLMs) factuality across three areas: Parametric, Search, and Multimodal reasoning.
19
29
248
📢 The FACTS Benchmark Suite is now live on Kaggle! Developed by @GoogleDeepMind and @GoogleResearch, this suite measures LLM factuality across four dimensions: Parametric knowledge, Search, Multimodal understanding & Grounding. Explore the leaderboard: https://t.co/O1bIoZqGCh
2
4
67
Huge congratulations to all the winners and thank you to every participant who made the Gemma 3n Impact Challenge a success! 👏🎉
Introducing the winners of the Gemma 3n Impact Challenge on @kaggle 🏆(🧵) Learn how the global developer community built with Gemma to address critical challenges and make a difference in people’s lives through the potential of on-device, multimodal AI.
0
7
77
If you participated in the 5-Day AI Agents Intensive Course with @Google and @kaggle this tweet is for you!📣 Share what you learned and built for a chance to win a DEV++ membership and exclusive badge! Enter by Sunday the 14th to be considered. #AIAgentsWritingChallenge #AI
2
7
31
Explore the benchmark and see how your models rank: 👇 https://t.co/u8BnmBHyLJ
kaggle.com
Evaluates language generation capabilities across diverse user-facing tasks in 29 Indic languages.
0
0
2
🚀 Benchmark your AI across India’s languages with IndicGenBench! Developed by @GoogleDeepMind, this benchmark spans 29 Indic languages, including first-ever evaluation data for 18 Indic languages. It supports language tasks like summarization, translation and question
2
5
67
Ivan Sorokin and I are the official winners on the Arc Prize competition, with a significant lead over other teams. Thanks to @kaggle and @arcprize for hosting the competition. NVIDIA tech blog summarizing what we did: https://t.co/BU8nHPCliJ Our writeup:
38
51
525
Hackathon Launch Alert! Vibe Code with Gemini 3 Pro in AI Studio hosted by @GoogleDeepMind 🎯Build real-world AI apps using Gemini 3 Pro in @GoogleAIStudio 💰Prize Pool: $500,000 in Credits ⏰Hackathon Timeline: Dec 5 - 12, 2025 (now extended!) https://t.co/IwVSFAjEg9
kaggle.com
Build with Gemini 3 and compete for $500,000 in credits
16
81
542
📢 5-Day AI Agents Intensive Course with @Google is now available as a self-paced Learn Guide! Access whitepapers, podcasts, codelabs & recorded livestreams 👇 https://t.co/HUCsnq9lEB
kaggle.com
9
144
840
Model Page: 👉 https://t.co/AhyoiKgeU0
kaggle.com
A new family of multimodal models from Google DeepMind
0
2
13
Did you check out the Gemini 3 Pro API on Kaggle yet? This model is accessible within the Kaggle environment for research, experimentation and competition use cases. More in 🧵…
1
19
131
🎉 Feature Update: You can now download Kaggle Benchmark leaderboard results! Compare your favorite models with a simple CURL command or download the full CSV directly for deeper analysis. 👉 Get started
kaggle.com
Use and download benchmarks for your machine learning projects.
2
10
64
AI is reshaping industries, but enterprise adoption lags. That's why we're partnering with @kaggle to deliver benchmarks that prove performance under real-world conditions. Learn how to choose AI you can trust: https://t.co/WH7x4kQ45e
5
21
76
💥 Special tier of the Gemini API for all participants 🎁 $500,000 in Gemini API Credits up for grabs Full participation details will be shared on December 5th! 👀 !
13
7
43
📌 Mark your calendars: December 5–7, 2025! @GoogleDeepMind’s Build the Future with Gemini 3 Pro hackathon is going live for two days! 🚀 We’re celebrating the launch of Gemini 3 Pro - Gemini’s most intelligent, capable and versatile model yet.
20
40
441
Welcome @MistralAI's Ministral 3 on Kaggle! Learn more:
kaggle.com
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 24GB of VRAM in FP8, and...
Introducing the Mistral 3 family of models: Frontier intelligence at all sizes. Apache 2.0. Details in 🧵
0
15
146
⚙️ AssetOpsBench: A unified framework for evaluating AI models and agents in industrial operations, using: • 2.3M+ sensor datapoints • 4,000+ work orders • Structured FMEA insights https://t.co/kQw6q5xQB7
kaggle.com
Evaluates LLMs against real-world industrial asset scenarios, including operation, maintenance, diagnostics, and decision support
0
0
0