AI Beats Human Writers in New Benchmark

A new benchmark from Vulsar AI suggests that advanced AI models can now outperform amateur human writers in long-form writing, though professional writers still maintain a clear advantage. The benchmark evaluated 475 prompts using 24 large language models against human writers, with GPT 6 Astra ranking first with an 87.8% predicted win rate.

However, Vulsar's separate evaluation of professional writers showed a stronger result than the amateur human baseline, indicating that AI has not yet surpassed professional creative writers. The results also revealed that strong creative writing performance remains concentrated among a small number of frontier AI systems, while humans still outperform AI in maintaining complex narratives over long stretches of text.

Brief written by urgent.news from ProPakistani's own syndicated text. Machine-written — may contain errors; check the original before relying on it.