#Benchmarks

Why GLM-5.2’s Low Hallucination Rate Upends the Enterprise LLM Stack

Z.ai’s MIT-licensed model challenges GPT-5.5 with a 3x lower hallucination rate and 1/7th the inference cost.

Article · 1w ago2

GLM-5.2 Claims Top Open-Weights Spot on Artificial Analysis

Z ai's latest model matches proprietary frontier performance on agentic benchmarks while keeping an open MIT license.

Article · 1w ago2

Claude Fable 5 Benchmarks Reveal Middling Security Fix Rates

New evaluation data shows Anthropic's latest model struggles with real-world security patches despite its impressive offensive capabilities.

Article · 2w ago7

Claude Fable 5: Anthropic ships its Mythos-class frontier model — deliberately handicapped

Fable 5 and Mythos 5 are literally the same model. The difference is a set of safety classifiers that quietly swap you down to Opus 4.8 when a request strays into offensive security or dual-use biology — and the benchmark asterisks show exactly where the governor bites.

News · 2w ago5

whichllm: Hardware-Aware LLM Rankings in One Command

Forget parameter count. This open-source CLI auto-detects your GPU, pulls live HuggingFace data, and ranks local models by real benchmark scores weighted for your exact rig.

Article · 3w ago0