Ortet self-hosts and benchmarks 34 open-weight models on 50 health tasks
kchonyc · x · 2026-10-27
Health AI startup Ortet benchmarked 34 recent open-weight models on 50 tasks from 15 public health benchmarks, alongside 8 closed frontier models (GPT-6 Astra/Sol/Luna, Claude Opus 5.5, Sonnet 5.5, etc.). Notably, 75% of the 34 models were released in the past six months—18 within three months and 4 within two weeks. All models are self-hosted on Ortet's NVIDIA Blackwell cluster (Orion) and served via their own API for reproducibility and data control. The team argues evaluation shapes training direction, and open weights enable a full evaluate-data-train-reevaluate loop for healthcare.
More from Infra
- Sail equivalence proof and riscv-coq cross-checks uncover real RISC-V spec bugs — xennygrimmato_ · 2026-10-27
- xAI's Colossus 1 hits ~14.6 exaflops FP64, ~5x Top500 leader — cis_female · 2026-10-27
- Lambda runs 19 B200 nodes in a 16-node power budget, boosting throughput 24% — TheZachMueller · 2026-10-27
- Podcast: Micron's HBM roadmap, Meta's AI infra, and NVIDIA's supply chain lock-in — BenBajarin · 2026-10-27
- SGLang MegaKernel + PD Pushes the TCO-Latency Frontier on GB300, SemiAnalysis Benchmarks Show — AccBalanced · 2026-10-27
- Scaling self-hosted Convex: compiling TypeScript Convex functions to WASM — leventov · 2026-10-27