cd/entity/MMMLU· home› entities› MMMLU
grep -l @mmmlu /news/*.json | wc -l → 1

MMMLU

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:02
2026-09-24
bottlecapai.com
large-language-models

ThinkingCap-Qwen3.8-27B: the same answers, 37% less thinking

Bottlecap AI released ThinkingCap-Qwen3.8-27B, a drop-in replacement for Qwen3.8-27B that cuts mean thinking tokens by 37.2% on average across twelve benchmarks for a macro-average accuracy cost of 0.…

// co-occurs with top 6 entities
Bottlecap AI 1 ThinkingCap-Qwen3.8-27B 1 Qwen3.8-27B 1 Qwen Team 1 HuggingFace 1 GPQA-Diamond 1
// topics top 4 topics
large language models 1 ai research 1 machine learning 1 artificial intelligence 1