BioSimBench tests whether LLMs can simulate biology — even top models only partly right
SimplyAnnisa · x · 2026-11-05
CellType introduced BioSimBench, a benchmark (built on NVIDIA infra) testing whether LLMs can simulate real lab experiments: predicting how cells respond to drugs, gene knockdowns, and immune signals. Even the best frontier models get only part of the response right, leaving lots of room for improvement. The post's thread also claims CellType's 27B model sits above every frontier model on this biology scoreboard.
More from Models
- Researcher laments the enormous cost of RL used to squash models' quirky behaviors — generativist · 2026-11-05
- Gemini 4 C arbon one-shots 4,000-line demo, users say Google fixed model laziness — theREALmarvin · 2026-11-05
- Ed Witten's new paper thanks Claude Opus 5.5 for assistance on many details — inductionheads · 2026-11-05
- DeepSeek alone handled 53% of OpenRouter's 27T daily tokens; open-weights labs top 75% — Comfortable-Rock-498 · 2026-11-05
- User screenshot shows ChatGPT desktop offering mystery models like 6 Luna and 5.6 Terra — flowersslop · 2026-11-05
- Kimi K3.1 Pro lands on Modal with expanded RL for coding and agentic work — blelbach · 2026-11-05