AI Paper Atlas

Research map / Benchmarks / SEED-Bench

SEED-Bench leaderboard

34 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SEED-Bench. Best accuracy: 81.1 (Bi-VRL, ECCV 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.

SEED-Bench · accuracy

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

#accuracy ↑MethodPaperTopic
181.1Bi-VRL
LLaDA-V
Reinforcement Learning for Multimodal Diffusion Language Models via Bidimensional Trajectory and Thought Optimization
ECCV 2026 · Table 1
Multimodal LLMs
278.29GPT-4o + VLB L3
GPT-4o
Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping
ICLR 2025 · Table: language bootstrapping
Multimodal LLMs
378.1ORION (Ours)
Qwen2.5-VL-7B
ORION: Decoupling and Alignment for Unified Autoregressive Understanding and Generation
ICLR 2026 · Table 3
Multimodal LLMs
477.5CoLT
Qwen3-VL-8B
CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts
ECCV 2026 · Table 1
Multimodal LLMs
576.5UniGen-1.5
Qwen2.5-7B
UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in RL
CVPR 2026 · Table 3
Text-to-image diffusion
676.1CofactGVRCofactGVR: Counterfactual Intervention for Grounded Visual Reasoning
ICML 2026 · Table 2
Multimodal LLMs
775.5Sa2VA-8BSa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos
TPAMI 2026 · Table 5
Video-language understanding
873.3DeSa2VA-4B
InternVL2.5-4b
Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
TPAMI 2026 · Table 2
Video-language understanding
972.5CogVLM-Chat
Vicuna-7B
CogVLM: Visual Expert for Pretrained Language Models
NeurIPS 2024 · VQA and LVLM table
Human and embodied modeling
1071.6SPHINX-2k
LLaMA-2-13B
"SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models"
ECCV 2024 · Table 1
Multimodal LLMs
7 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

SEED-Bench · score

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

#score ↑MethodPaperTopic
176.5Qwen2-VL-7B+Critic-V
Qwen2-VL-7B
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
CVPR 2025 · Main results table
Multimodal LLMs
276.21SpatialReasoner-R1 fDPO 8B
InternVL2.5
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
NeurIPS 2025 · Table: General Vision-Language
Multimodal LLMs
376.2SAMA-8B
Sa2VA-8B
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
NeurIPS 2025 · Table 3
Video-language understanding
474.1UVU
Qwen2.5-3B-Instruct
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
CVPR 2026 · Table 4
Multimodal LLMs
573.64MuNG
Qwen2.5-VL-3B
Explore How to Inject Beneficial Noise in MLLMs
AAAI 2026 · Table 1
Multimodal LLMs
671.8EvoTok (Ours)
Qwen-2.5-7B-Instruct
EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
ECCV 2026 · Table 2
Autoregressive and latent generation
770.8UniGen
Qwen2.5-1.5B
UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
NeurIPS 2025 · Image understanding results ta
Multimodal LLMs
870.5JanusFlow
DeepSeek-LLM 1.3B
JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
CVPR 2025 · Table 4
Human and embodied modeling
964.2HAMSTER
VILA1.5-13B
HAMSTER: Hierarchical Action Models for Open-World Robot Manipulation
ICLR 2025 · Table: Core VQA and robustness
Robot action and navigation
1063.7Janus
DeepSeek-LLM 1.3B
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
CVPR 2025 · Table 2
Human and embodied modeling
7 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.