APIUp to 25% cheaper than official pricesTry the API →
Hermes
APIModelsCases
Back to News
newsBenchmarksLlms

Artificial Analysis' MLCR-AA Shows Most AI Models Fail Medical Reasoning

A new leaderboard scores frontier models on synthesizing 70 to 150 page medical case files, with Claude Fable 5 leading at 64.4 percent.

Artificial Analysis' MLCR-AA Shows Most AI Models Fail Medical Reasoning
Source
Artificial Analysis
Published
Author
AlphaSignal Newsroom
Read
1 min read

A new leaderboard scores frontier models on synthesizing 70 to 150 page medical case files, with Claude Fable 5 leading at 64.4 percent.

Reporting is indexed from AlphaSignal. Rights remain with the original publisher and cited sources.

Read original report

Next reads

Vals AI's Science Index Puts GPT-6 Astra Above Gemini 4 Argon
Vals AI · news

Vals AI's Science Index Puts GPT-6 Astra Above Gemini 4 Argon

Google's Gemini 4 Argon Rewrites Chromium and Frees 300 TiB With 1M-Token Outputs
Google DeepMind · news

Google's Gemini 4 Argon Rewrites Chromium and Frees 300 TiB With 1M-Token Outputs

DeepPhylo Uses Discrete Diffusion to Map Evolutionary Trees From DNA
AlphaSignal · paper

DeepPhylo Uses Discrete Diffusion to Map Evolutionary Trees From DNA