Pith. sign in

REVIEW 12 cited by

MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.16006 v1 pith:BM3DIATA submitted 2024-04-24 cs.CV

classification cs.CV
keywords multimodalmmt-benchlvlmsevaluationmodelstasksvisualbenchmark
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Large Vision-Language Models (LVLMs) show significant strides in general-purpose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in tracking LVLM development. In this study, we present MMT-Bench, a comprehensive benchmark designed to assess LVLMs across massive multimodal tasks requiring expert knowledge and deliberate visual recognition, localization, reasoning, and planning. MMT-Bench comprises $31,325$ meticulously curated multi-choice visual questions from various multimodal scenarios such as vehicle driving and embodied navigation, covering $32$ core meta-tasks and $162$ subtasks in multimodal understanding. Due to its extensive task coverage, MMT-Bench enables the evaluation of LVLMs using a task map, facilitating the discovery of in- and out-of-domain tasks. Evaluation results involving $30$ LVLMs such as the proprietary GPT-4V, GeminiProVision, and open-sourced InternVL-Chat, underscore the significant challenges posed by MMT-Bench. We anticipate that MMT-Bench will inspire the community to develop next-generation multimodal foundation models aimed at achieving general-purpose multimodal intelligence.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning

    cs.AI 2026-04 unverdicted novelty 8.0 of 10

    FeynmanBench is the first benchmark for evaluating multimodal LLMs on diagrammatic reasoning with Feynman diagrams, revealing systematic failures in enforcing physical constraints and global topology.

  2. CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    CoLT teaches multi-modal models to reason in a few latent steps with temporary dual-mode decoder supervision, cutting inference time ~10× versus text CoT while beating prior latent methods.

  3. Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents

    cs.AI 2025-12 unverdicted novelty 6.0 of 10

    Argos is an agentic verifier that adaptively picks scoring functions to evaluate accuracy, localization, and reasoning quality, enabling stronger multimodal RL training for AI agents.

  4. Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis

    cs.CV 2025-09 reject novelty 6.0 of 10

    MMOral is a large new dental X-ray instruction dataset and benchmark, but the proposed model's 24.73% improvement is from fine-tuning and then testing on the same data pool.

  5. SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models

    cs.AI 2025-08 unverdicted novelty 6.0 of 10

    SEAM measures VLM reasoning consistency across modalities using paired semantically equivalent textual and visual notations, and finds systematic vision-language imbalance.

  6. HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A hierarchical benchmark for multimodal models on human-centric visual understanding finds frontier models average under 60% and miss question-uncued visual evidence, with test-time scaling helping only marginally.

  7. MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A new 2,700-task benchmark with budget, time, and distance constraints shows that even the best multimodal LLMs produce feasible plans less than 22% of the time.

  8. COREVQA: A Crowd Observation and Reasoning Entailment Visual Question Answering Benchmark

    cs.CV 2025-07 conditional novelty 6.0 of 10

    COREVQA introduces a 5,608-pair true/false visual entailment benchmark for crowd images on which the strongest tested vision-language models reach only 77.57% accuracy.

  9. Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Grid-based prompting lets GPT-4o georeference textual locality descriptions from natural history records using map excerpts, averaging about 1.03 km error on a 25-example dataset.

  10. MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI

    cs.AI 2025-06 conditional novelty 6.0 of 10

    MMReason is an open-ended multimodal reasoning benchmark that filters out guessable and memorized questions and scores model answers both by final answer and by intermediate steps.

  11. CoMemo: LVLMs Need Image Context with Image Memory

    cs.CV 2025-06 conditional novelty 6.0 of 10

    CoMemo adds a cross-attention image-memory path and thumbnail-anchored position encoding to reduce visual neglect in long-context and multi-image LVLM tasks.

  12. ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Interleaving key video frames into step-by-step reasoning improves video question answering by 1.7 to 5.5 points over text-only chain-of-thought on a new self-built benchmark.

Pith tools