AI Paper Atlas

Research map / Benchmarks / LLaVA-Bench

LLaVA-Bench leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on LLaVA-Bench. Best score: 91.4 (LLaVA-OV-7B + SPR, ICCV 2025).

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.

LLaVA-Bench · score

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

#score ↑MethodPaperTopic
191.4LLaVA-OV-7B + SPR
LLaVA-OV-7B
Spatial Preference Rewarding for MLLMs Spatial Understanding
ICCV 2025 · Table 6
Multimodal LLMs
287.3Qwen2.5VL-7B + IPA
Qwen2.5VL-7B
Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs
ICCV 2025 · Table 1
Multimodal LLMs
379.2STIC
LLaVA-v1.6 (7B)
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
NeurIPS 2024 · Table 1
Multimodal LLMs
478.8GPT-4o V2+L3 (easy)
GPT-4o
Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
ICLR 2025 · Table: hardest and easiest com
Multimodal LLMs
575.1DAMA
LLaVA-1.5-13B
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
ICML 2025 · Table: Performance comparisons
Alignment and preferences
671.5RoboCodeX-13B
LLaMA-13B
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
ICML 2024 · Table: Performance on general
Robot action and navigation
767.6+RePer
LLaVA-1.5 13B
Perception in Reflection
ICML 2025 · Table 1
Multimodal LLMs
866.9CoMemo
InternLM-1.8B
CoMemo: LVLMs Need Image Context with Image Memory
ICML 2025 · Table 2
Multimodal LLMs
966.5HiMAP
LLaVA-7B
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
CVPR 2025 · Table 3 (natural QA)
Multimodal LLMs
1065TG-LLaVA
Vicuna-7B
TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings
AAAI 2025 · Table 1
Multimodal LLMs
4 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.