←Back to NewsAI News/LlmsnewsLlmsBenchmarksLiquid AI's LFM2 Beats GPT-5 and Claude on Aging Research TasksLiquid AI and Insilico Medicine released two small LFM2 variants that beat GPT-5, Gemini-3.1-Pro, and Claude Opus on aging biology benchmarks.SourceLiquid AIPublishedSep 17, 2026, 3:29 PMAuthorAlphaSignal NewsroomRead1 min readLiquid AI and Insilico Medicine released two small LFM2 variants that beat GPT-5, Gemini-3.1-Pro, and Claude Opus on aging biology benchmarks.Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.Read original report ↗Next readsEpoch AI · newsEpoch Audits 15 AI Benchmarks and Flags Nine as FlawedAlphaSignal · paperMax Planck's talkie-1930-13b Shattered People's Nostalgia for a Moral PastArtificial Analysis · newsOpenBMB's MiniCPM5-2B Tops Sub-4B Charts While Burning 3x Fewer Tokens
