Tagged: model-benchmarks

6 articles

Latest

AI Benchmarks Lie: Safety and Reasoning Scores Are Dangerously Entangled

GLM-5.3 ties for top open model but Z.ai holds back weights over security fears

Ling 3.0 Flash hits 38 on AI index, beats Qwen3.6 27B at a fraction of the cost

Liquid AI's new 230M encoder runs 3.7x faster than ModernBERT on CPU at 8K tokens

Anthropic's Opus 5 lands at half the cost of Fable, but skips the big leap

Stop Crushing 70B Quants: The 6 Models That Actually Run Well on a 24GB GPU in 2026