Measuring the "emotional intelligence" of a local LLM — Benchmarking Qwen3.5-122B(int4) with EQ-Bench 3

We've published a new article on Zenn: "Measuring the "emotional intelligence" of a local LLM — Benchmarking Qwen3.5-122B(int4) with EQ-Bench 3".

An English (machine-translated) version is available:

https://zenn.dev/quixotiks/articles/89273f2e2338b5?locale=en