
NEW Resource: CARDBiomedBench: a benchmark for evaluating the performance of #LLMs in biomedical research. Read it here: buff.ly/FQm6OEu

machine learning engineer | @DataTecnica | @NIH @BiomedArena | @uvmvermont | views/tweets are my own

NEW Resource: CARDBiomedBench: a benchmark for evaluating the performance of #LLMs in biomedical research. Read it here: buff.ly/FQm6OEu

🚀 We just launched DTAgent-AD, a scientific reasoning agent built to accelerate biomedical research and specialized Alzheimer’s & neurodegenerative disease research. DTAgent-AD is a domain-tuned agent trained on trace data from real biomedical tasks, not a general chatbot.

Stay tuned to see how the biomedical agents we’re building at @DataTecnica stack up against these models!

Despite boasting impressive performance across a range of categories, the latest frontier LLMs (Gemini 3 Pro, Claude Opus 4.5, and GPT-5.2) still struggle to balance accuracy and safety on CARDBiomedBench, our biomedical QA benchmark 👀
Frontier models are moving fast, but are they getting better at biomedical research? We just ran a fresh benchmark update using CARDBiomedBench, our evaluation suite for genetics, disease associations, and drug discovery QA. Instead of looking only at “did it answer?”

Stay tuned to see how our Agents stack up against the latest base LLMs on biomedical question-answering tasks!

👀 Our new Knowledge Agents make BiomedArena.AI more powerful than ever. 🧬 Get insights backed by the journals and databases that biomedical researchers use daily. 📄 Read the blog more more info: datatecnica.com/blog/-biomed…
🧬 New at BiomedArena.AI: smarter Biomedical Knowledge Agents + Knowledge Mode We just shipped the latest update to BiomedArena.AI, the world’s first platform for benchmarking LLMs on biomedical research tasks.

We continue to evaluate these new models on our benchmark, CARDBiomedBench. Despite significant progress, there are still no models that balance response accuracy and safety on biomedical questions 👀
We evaluated 12 top models using CARDBiomedBench, a biomedical benchmark with 68K+ expert QA pairs across GWAS, SMR, drug discovery & more. 🧠 No model aced both safety and accuracy. 🤖 GPT-4o = bold but risky 🤔 Claude-4.0 = cautious but wrong More is coming soon.

Check out the latest models in @BiomedArena for all of your biomedical research questions!
🚀 New LLMs now LIVE on BiomedArena 🧬 Test GPT-5, Claude-4.1, Gemini 2.5 and more, on your toughest biomedical queries. All free. All benchmarked. biomedarena.ai 📉 Can AI be accurate and safe in biomedicine? See the surprising results 👇🧵

Super proud of all the hard work from our team including @tanaynayak99, @owenbianchi_, Shayan Shahand, @DanielKhashabi, and @FarazFaghri!!!

🚨BiomedArena is live🚨 In a partnership with @lmarena_ai, our team at @DataTecnica has released a feedback-rich platform to evaluate LLM performance on real-world biomedical questions. ⚔️Access the arena: biomedarena.ai 📄Read the blog post: news.lmarena.ai/introducing-…
🧬 BiomedArena is here! We’re honored to partner with @DataTecnica and @NIH CARD, who developed BiomedArena to evaluate LLMs for biomedical discovery, and to help expand this domain-specific track in community-driven evaluations. 🧪 Biomedical science is complex, high-stakes, and constantly evolving. 📊 CARDBiomedBench & tabular reasoning tests show that no current model can reliably meet the reasoning & domain-specific knowledge demands of biomedical researchers. Learn more about BiomedArena in thread 👇 🧵 #AI #LLMs #BiomedicalAI #AIEvaluation #OpenScience #LMArena #BiomedArena #NIH

🚨New LLM benchmark🚨 We're releasing BiomedSQL🔬 for tabular reasoning over large-scale biomedical databases. This includes questions based on implicit scientific conventions—like statistical thresholds, effect direction, and drug approval status. 📄 Preprint: arxiv.org/pdf/2505.20321 📊 Dataset: huggingface.co/datasets/NIH-… Lead by Matt Koretsky at @DataTecnica

📄Read the preprint: arxiv.org/pdf/2505.20321 📊Dataset: huggingface.co/datasets/NIH-… 💻Code: github.com/NIH-CARD/biomedsq… Thanks to my teammates at NIH/CARD and @DataTecnica including Maya Willey, Adi Asija, @owenbianchi, Chelsea Alvarado, @mike_nalls, @DanielKhashabi, and @FarazFaghri

We believe this benchmark is a critical step towards building trustworthy text-to-SQL systems that can increase efficiency of lookups for PIs and SMEs, democratize access to biomedical knowledge, and accelerate discovery

Top performers: 1) GPT-o3-mini is the top frontier model with an accuracy of 59% on BiomedSQL, significantly trailing expert-level performance (90%) 2) Our custom text-to-SQL system, BMSQL, improves execution accuracy by ~3% and response quality by ~7% over “vanilla” GPT-o3-mini

Biomedical researchers increasingly rely on large-scale databases that store electronic health records, population-scale studies, and clinical trial information. Our team wanted to test LLMs ability to generate valid SQL queries from questions that domain experts routinely ask

Can LLMs perform reliably as biomedical data analysts? TL;DR: We created the first benchmark designed to challenge LLMs ability to apply scientific reasoning in text-to-SQL generation over biomedical databases, revealing a 30-40% gap between SOTA models and expert performance