# What We are Missing in Multimodal LLM Evaluation?

arXiv: https://arxiv.org/abs/2606.26348 · HTML: https://mlsanity.com/paper/2606.26348/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 7 of 7)

- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2412.18194/) (2024)
- [Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives](https://mlsanity.com/paper/2501.04003/) (2025)
- [VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR](https://mlsanity.com/paper/2505.17423/) (2025)

## Abstract (arXiv)

Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced rapidly, evaluation of such models has not kept pace. Most existing evaluation benchmarks are limited to isolated tasks and reveal little about whether a model integrates information across modalities. We examine current means for evaluating MLLMs and review the existing benchmark taxonomy to identify gaps, including temporal-spatial coherence, physical world understanding, multimodal consistency, and selective attention. Addressing these gaps is essential for measuring real progress in multimodal intelligence and exposing capability boundaries.