IFMTBench

What is IFMTBench?

Evaluates multilingual translation systems on instruction following across seven languages, six constraint types, and compositional multi-constraint requests.

Released

2026-05-27

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.28218

IFMTBench paper and code

• Paper https://arxiv.org/abs/2605.28218
• Code https://github.com/Tencent-Hunyuan/Hy-MT2/tree/main/IFMTBench

Which sources cite IFMTBench?

• IFMTBench

Related General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench