# TR Benchmarking Suite: TR-MMLU + Mukayese + TruthfulQA-TR + BBQ-TR + Custom

> Source: https://sukruyusufkaya.com/en/learn/fine-tuning-cookbook/ftc-tr-benchmarking-suite
> Updated: 2026-05-14T14:42:56.838Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part IX — Turkish-First & Localization Engineering
**TLDR:** Standard suite for evaluating FT models in TR: TR-MMLU (general knowledge, Boğaziçi), Mukayese (TR NLP tasks), TruthfulQA-TR (hallucination), BBQ-TR (bias). Automated with lm-eval-harness. CI integration, regression alarms.