MLCR-AA Updated: Benchmarking LLMs on 25k–64k Token Medical Records
ArtificialAnlys · x · 2026-10-21
Artificial Analysis has updated its MLCR-AA methodology and results. The benchmark from Wisedocs tests reasoning over long, fragmented medical records (25k–64k tokens each), requiring the multi-document synthesis claims professionals do: reconstructing chronology, causality and treatment patterns. A panel of three LLM judges scores responses against expert-annotated ground truth, reporting pass rate, accuracy and completeness. MLCR-AA uses a private held-out set of the two hardest difficulty tiers (60 questions, each run 3 times), evaluated independently by Artificial Analysis.
More from Models
- Recursive AI ships Flint, a 40B-A2.5B MoE claimed to match Qwen3.6-27B, weights on Hugging Face — ChengleiSi · 2026-10-22
- DeepSeek ships V4.1-Flash-1017, now the #1 open model on RSI-Inference Bench — scaling01 · 2026-10-22
- OpenAI's Cybersecurity Guardrails Block a Dev From Auditing His Own Patched Server — Next_Technology6361 · 2026-10-22
- TPN-006 hits Hugging Face: 7.7GB compressed model beats its 17GB Mistral teacher — markjeffrey · 2026-10-22
- Kimi K3.1's latest checkpoint draws 49k-token SVG portrait zero-shot in 22 minutes — lyraxana · 2026-10-22
- MiniMax launches M3.1 Flash at 1/3 the cost and 3x the speed of M3, weights out Oct 23 — MiniMax_AI · 2026-10-22