AI Paper Atlas

Research map / Benchmarks / A-OKVQA

A-OKVQA leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on A-OKVQA. Best accuracy: 87.5 (SoT, NeurIPS 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

A-OKVQA · accuracy

15 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
187.5SoT
Qwen2.5-VL-7B
State of Thought Enables Endogenous Reasoning
NeurIPS 2026 · Table 5
Reasoning and chain of thought
284.59SearchLVLMs with InternVL-1.5
InternVL-1.5
SearchLVLMs: A Plug-and-Play Framework for Augmenting Large Vision-Language Models by Searching Up-to-Date Internet Knowledge
NeurIPS 2024 · Table 2
Visual question answering
381.4HiMAP
LLaVA-13B
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
CVPR 2025 · Table 1
Multimodal LLMs
481.25AttentionPack (R=64)
LLaVA1.5-13B
Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding
CVPR 2026 · Table 1
Multimodal LLMs
580.5LLaVA-1.5-13B w/ FastV (K=0, R=50%)
LLaVA-1.5-13B
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
ECCV 2024 · Table 4
Multimodal LLMs
678.3CARVE
Qwen2.5-VL-3B
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
ECCV 2026 · Table 1
Multimodal LLMs
772.4LLaVA-1.5 + Q&A Prompts
LLaVA-1.5
Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge
ECCV 2024 · Table 2
Visual question answering
864.1InstructBLIP w/ VIGC
InstructBLIP
VIGC: Visual Instruction Generation and Correction
AAAI 2024 · Table 4
Multimodal LLMs
962.5HYDRA w LLaVA1.5 (7B)
LLaVA1.5 (7B)
HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning
ECCV 2024 · Table 5
Multimodal LLMs
1060.6CoMEM + Qwen2VL
Qwen2-VL
Towards General Continuous Memory for Vision-Language Models
NeurIPS 2025 · Main results table
Multimodal LLMs
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.