Multimodal Reasoning

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

11 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 138 papers with code (302 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
  24 May 2025 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified
  We showcase the utility of this dataset through: 1) improving infographic chart understanding via fine-tuning, 2) benchmarking code generation for infographic charts, and 3) enabling example-based infographic chart…
• WebQA: Multihop and Multimodal QA
  1 Sep 2021 3 repositories listed Syntology ran 4 of 13 samples · 9 unverified · 12 pointer-only (licence)
  Scaling Visual Question Answering (VQA) to the open-domain and multi-hop nature of web searches, requires fundamental advances in visual representation learning, knowledge aggregation, and language generation.
• e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
  7 Apr 2020 3 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning.
• Skywork-R1V3 Technical Report
  8 Jul 2025 2 repositories listed Syntology ran 3 of 12 samples · 9 unverified · 12 pointer-only (licence)
  The strong performance of Skywork-R1V3 primarily stems from our elaborate post-training RL framework, which effectively activates and enhances the model's reasoning ability, without the need for additional continue…
• Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
  28 May 2025 2 repositories listed
  Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress.
• Emerging Properties in Unified Multimodal Pretraining
  20 May 2025 2 repositories listed Syntology ran 9 of 21 samples · 12 unverified
  Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems.
• MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
  19 May 2025 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  While Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language understanding, they still struggle with complex multi-step reasoning, often producing logically inconsistent or…
• SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information
  19 May 2025 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  While their performances on speech and audio-processing tasks are extensively studied, their reasoning abilities remain underexplored.
• VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
  10 Apr 2025 2 repositories listed Syntology ran 2 of 12 samples · 10 unverified
  By combining these two techniques, our model, VL-Rethinker, advances state-of-the-art scores on MathVista, MathVerse to achieve 80.
• The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
  3 Feb 2025 2 repositories listed
  Our results reveal that o-[n] series, particularly later iterations like o3 and o4-mini, significantly outperform the GPT-[n] series and show strong scalability in multimodal reasoning.
• LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
  15 Nov 2024 2 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Large language models have demonstrated substantial advancements in reasoning capabilities, particularly through inference-time scaling, as illustrated by models such as OpenAI's o1.
• Distill Visual Chart Reasoning Ability from LLMs to MLLMs
  24 Oct 2024 2 repositories listed Syntology ran 0 of 13 samples · 13 unverified · 13 pointer-only (licence)
  Specifically, we employ text-based synthesizing techniques to construct chart-plotting code and produce ReachQA, a dataset containing 3k reasoning-intensive charts and 20k Q&A pairs to enhance both recognition and…
• MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models
  2 Aug 2024 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  Motivated by this, we introduce MuChoMusic, a benchmark for evaluating music understanding in multimodal language models focused on audio.
• PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns
  20 Mar 2024 2 repositories listed Syntology ran 13 of 14 samples · 1 unverified
  To diagnose the reasoning challenges in large multimodal models, we progressively guide the models with our ground truth reasoning explanations for visual perception, inductive reasoning, and deductive reasoning.
• Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning
  6 Mar 2024 2 repositories listed
  We present a new dataset, AlgoPuzzleVQA designed to challenge and evaluate the capabilities of multimodal language models in solving algorithmic puzzles that necessitate both visual understanding, language…
• MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks
  13 Oct 2023 2 repositories listed
  Consequently, our work complements research on the performance of MLLMs in multimodal comprehension tasks, achieving a more comprehensive and holistic evaluation of MLLMs.
• Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language Models
  26 May 2023 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Therefore, we propose Graph-of-Thought (GoT) reasoning, which models human thought processes not only as a chain but also as a graph.
• Multimodal Analogical Reasoning over Knowledge Graphs
  1 Oct 2022 2 repositories listed Syntology ran 7 of 27 samples · 20 unverified
  Analogical reasoning is fundamental to human cognition and holds an important place in various fields.
• Dual Attention Networks for Multimodal Reasoning and Matching
  2 Nov 2016 2 repositories listed
  We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language.
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  6 Jul 2025 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 3 pointer-only (licence)
  Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation.
• GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
  1 Jul 2025 1 repository listed Syntology ran 0 of 11 samples · 11 unverified
  In a comprehensive evaluation across 28 public benchmarks, our model outperforms Qwen2.
• Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
  30 Jun 2025 1 repository listed
  (1) We establish the foundational principles of the think with image paradigm and its three-stage framework.
• HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
  26 Jun 2025 1 repository listed
  With the rapid evolution of multimodal large language models, the capacity to deeply understand and interpret human intentions has emerged as a critical capability, which demands detailed and thoughtful reasoning.
• Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
  20 Jun 2025 1 repository listed Syntology ran 0 of 17 samples · 17 unverified · 17 pointer-only (licence)
  Vision-language models (VLMs) excel at multimodal understanding, yet their text-only decoding forces them to verbalize visual reasoning, limiting performance on tasks that demand visual imagination.
• Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
  16 Jun 2025 1 repository listed
  Recent advancements in large language models (LLMs) have witnessed a surge in the development of advanced reasoning paradigms, which are now being integrated into multimodal large language models (MLLMs).
• Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
  11 Jun 2025 1 repository listed
  To address the limitations, we propose drawing to reason in space, a novel paradigm that enables LVLMs to reason through elementary drawing operations in the visual space.
• Play to Generalize: Learning to Reason Through Game Play
  9 Jun 2025 1 repository listed Syntology ran 0 of 12 samples · 12 unverified
  Developing generalizable reasoning capabilities in multimodal large language models (MLLMs) remains challenging.
• WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning
  9 Jun 2025 1 repository listed
  (2) The open-source WeThink dataset containing over 120K multimodal QA pairs with annotated reasoning paths, curated from 18 diverse dataset sources and covering various question domains.
• Learning Compact Vision Tokens for Efficient Large Multimodal Models
  8 Jun 2025 1 repository listed
  Specifically, we propose a Spatial Token Fusion (STF) method to learn compact vision tokens for short vision token sequence, where spatial-adjacent tokens are fused into one.
• MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
  5 Jun 2025 1 repository listed
  Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions.

Syntology lines on 18 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.