Benchmark RadarAI BENCHMARK PROFILE
JOR-Bench
JOR-Bench is a collection of five Japanese-language benchmarks for LLMs in operations research, covering 1,319 problems from IndustryOR, MAMO, NL4OPT, OptiBench, and OptMATH, with pairs of Japanese problem statements and numerical answers.
- Released
- 2026-07-18
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Provides a standardized Japanese-language evaluation for OR formulation and solving, enabling cross-lingual comparison and highlighting language-specific issues.
Motivation
We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.