{"version":1,"type":"story","url":"https://digestai.news/story/h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate","json":"https://digestai.news/story/h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate.json","markdown":"https://digestai.news/story/h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate.md","slug":"h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate","headline":"H2O.ai’s TimeH2O-v1 tops time-series benchmarks with 91.9% win rate","summary":"It achieved a 91.9% win rate and a 50.8% lower forecast error than a seasonal-naive baseline across 100 forecasting tasks. The model handles univariate series and covariates, covering finance, healthcare, supply chain, and energy—without fine-tuning on fev-bench data. TimeH2O-v1 has 108 million parameters and is available on Hugging Face under a non-commercial license for internal testing. Commercial users must contact H2O.ai directly.\n\nThe company positions TimeH2O-v1 as a zero-shot forecasting tool that organizations can fine-tune for domain-specific use. H2O.ai emphasizes its ‘Sovereign AI Platform,’ which supports production deployment across cloud and air-gapped environments. The model’s performance aligns with its mission to democratize AI forecasting for regulated sectors like finance and healthcare, where accuracy and governance are critical.","keyPoints":["TimeH2O-v1 leads fev-bench with 91.9% win rate, 50.8% lower error than baseline across 100 tasks","Model handles univariate series and covariates (e.g., price, weather) with 108M parameters","Available on Hugging Face under non-commercial license; commercial access requires direct contact"],"whyItMatters":"A zero-shot time-series model this accurate could reduce costs for industries like retail, energy, and healthcare by cutting manual model retraining and improving demand planning.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":["H2O.ai","AT&T","Commonwealth Bank of Australia","Wells Fargo","Bank of America","Workday"],"models":["TimeH2O-v1","Timestral-209M","t0-gamma","TimesFM-3","Chronos-2"],"people":["Sri Ambati"]},"firstPublishedAt":"2026-10-26T04:28:00Z","updatedAt":"2026-10-26T04:28:00Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"aol.com","title":"H2O.ai's TimeH2O Beats Mistral, Google, and Amazon in Time-Series Forecasting","url":"https://aol.com/articles/h2o-ais-timeh2o-beats-mistral-152900000.html","publishedAt":"2026-10-26T04:28:00Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"The Escalating Battle for Time Series AI Dominance","url":"https://digestai.news/thread/mistral-ai-releases-timestral-forecasting-model-family-beats-google-timesfm-3","storyCount":2},"cite":{"text":"Digest AI, \"H2O.ai’s TimeH2O-v1 tops time-series benchmarks with 91.9% win rate\", 26 October 2026, https://digestai.news/story/h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate","publisher":"Digest AI","title":"H2O.ai’s TimeH2O-v1 tops time-series benchmarks with 91.9% win rate","datePublished":"2026-10-26T04:28:00Z","url":"https://digestai.news/story/h2o-ais-timeh2o-v1-tops-time-series-benchmarks-with-91-9-win-rate"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}