NVIDIA open-weight model ties pplx-decider at #1 on 669-case clinical benchmark
MaziyarPanahi · x · 2026-10-16
Maziyar Panahi congratulates NVIDIA on tying Perplexity's pplx-decider for #1 on a clinical decision benchmark, with both models released as open weights on Hugging Face.
Methodology details: every model is evaluated on the same 669 synthetic clinical decisions, prompts are never collected, and full per-row results with robustness analysis are published.
More from Models
- NEURA launches Neuron AI, a multimodal PLA model giving robots touch, force feedback and memory — CyberRobooo · 2026-10-17
- Sentience claims per-user models: train, continually update and serve one model per person — soleio · 2026-10-17
- Four Gemini 4 Argon agents beat Minecraft in 27 hours, writing 2,783 programs — GoogleDeepMind · 2026-10-17
- Meta open-sources Muse Spark Open to mixed reception: 'trash' license, nerfed benchmark scores — gabriberton · 2026-10-17
- If new diffusion models are open-weight only, what's left for commercial use? — blackpanda8484 · 2026-10-17
- Reflection Beam OSS architecture: sliding window attention, gated attention, QK Norm — A_K_Nain · 2026-10-17