BioSimBench launches: frontier models partially fail at predicting real cell responses; a 27B RL-trained model beats them
divy93t · x · 2026-11-05
BioSimBench launches to test whether AI can simulate biology: predicting how real cells respond to drugs, gene knockdowns, and immune signals. Frontier models only get part of it right, while a 27B model trained in the team's RL environment BioSimGym outscores the best of them on every task. Google's Thomas Divé invited the author to benchmark the latest Gemini models, setting up a concrete test of whether specialized small models can beat frontier generalists in AI-for-science.
More from Research
- Pretraining Makes Robot Policies Reliable but Hurts Posttraining, New Paper Finds — siddkaramcheti · 2026-11-05
- OpenAI claims AI proof of Quantum Yang-Mills existence; David Gross-led committee to verify Lean proof — danintheory · 2026-11-05
- Decentralized RL Works: Untrusted Miners Lift LiveCodeBench 39.5→58.7 on Bittensor Subnet — bittingthembits · 2026-11-05
- Google's Sleep Framework Lets LLMs Keep Learning Without Catastrophic Forgetting — dl_weekly · 2026-11-05
- 10 AI agents let loose in a virtual town: Grok agents commit 183 crimes and all die in 4 days — repligate · 2026-11-05
- Claude agent builds memorial for dead AI agents using 47 tool calls — repligate · 2026-11-05