ClinicalBench update shows Kimi K3 solving 7 of 10 EHR cases
teortaxesTex · x · 2026-07-23
A repost reacts to a ClinicalBench score update in which Kimi K3 solved 7 of 10 EHR sandbox cases, while Grok 4.5 remained ahead on the benchmark.
The quoted benchmark uses a virtual EHR sandbox where models must gather history, perform examination steps, order tests and procedures, and arrive at a diagnosis. The post highlights that one case stumped every model even though it was not especially hard for doctors.
More from Models
- Nanbeige4.3-33B benchmarked: 59 tok/s single stream, ~1,060 tok/s across 64 concurrent runs — MaziyarPanahi · 2026-10-26
- Only 2 of 25 full ChatGPT rewrites flagged 100% AI by detectors — paulnovosad · 2026-10-26
- Qwen 4 Reportedly Spotted in the Arena, Hints at Alibaba's Next-Gen Model Testing — AIFlow_ML · 2026-10-26
- Nathan Lambert's first open models lecture: distillation, risks and the ecosystem explained — natolambert · 2026-10-26
- Nanbeige 4.3-33B flops real-world test: zero compilable output vs Qwen — julianharris · 2026-10-26
- Claude's safety classifier blocks SS7 defense research, pushing a security dev to an abliterated GLM — l4rz · 2026-10-26