MMTIT-Bench

MMTIT-Bench A Multilingual and Multi-Scenario Benchmark with Cognition–Perception–Reasoning Guided Text-Image Machine Translation 中文版 • Paper • GitHub • HuggingFace Overview MMTIT-Bench is a human-verified benchmark for end-to-end Text-Image Machine Translation (TIMT). It contains 1,400 images spanning 14 non-English a

Papers using MMTIT-Bench (3)

MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation2026AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs2025MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI2024 · 6 cites