Model Benchmarks

Compare the performance of different AI models across standardized benchmarks. Higher scores generally indicate better performance, but context matters for each benchmark.

Benchmarks

Japanese MT-Bench - Humanities and Social Sciences Tasks

Benchmark performance of Fugaku-LLM in humanities and social sciences tasks, showcasing its proficiency in these areas.

Rank	Model	Provider	Score (score)	Date	Source
1	Fugaku-LLM	Fujitsu	9.18	May 4, 2025	View