Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Multimodal Understanding research benchmarks – Page 9 · SOTA2 Research

Multimodal Understanding

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

3.61Speedup Ratio (S)

8

Jun 2, 2026

MMMU-Pro overall (test)

28.44Score

8

May 22, 2026

MMMU, MMVet, RealWQA, ChartQA, MathVerse, MathVision, MathVista Aggregate

57.37Weighted Average Score

8

May 21, 2026

76Accuracy

8

May 18, 2026

Cross-LVLM (Aggregate of GQA, GMAI-MMBench, POPE, MME-Finance, MMMU_Pro, LLaVA-Wild) (test)

13.8ECE

8

May 12, 2026

2,457.1Overall Score

8

May 26, 2026

Aggregate Audio-Visual & Video Benchmarks

Full Model (Qwen2.5-Omni-7B)

57.6Avg Audio-Visual Score

8

Feb 26, 2026

MiMo-VL-7B-SFT-2508

2,473.6Score

8

Apr 14, 2026

SketchThinker-R1-3B

55.9Accuracy

8

Feb 26, 2026

Composite VLM Benchmark Suite

74.5Overall Average Score

8

Feb 26, 2026

60.52Accuracy

8

Feb 26, 2026

58.4Accuracy

8

Feb 26, 2026

MMBench Chinese (test)

63.6Accuracy

8

Feb 26, 2026

0.845Flickr30k Score

8

Feb 26, 2026

Aggregate All Tasks

Nemotron-Labs-Diffusion-VLM-8B

59.5Accuracy

7

Jul 8, 2026

Standard MLLM Benchmarks (GQA, MMB, MMB-CN, MME, POPE, SQA, TextVQA)

63.1GQA Accuracy

7

Jun 24, 2026

Multimodal Evaluation Suite GQA, SQA-I, VQA-T, MME, VQAv2, MMB

59.7GQA Score

7

Apr 28, 2026

66.7Score

7

Apr 23, 2026

85Score

7

Apr 23, 2026

VQAv2, GQA, VQAText, MMB, MMVet

81.2VQAv2 Accuracy

7

Mar 17, 2026

MLLM Evaluation Suite (GQA, MMBench, MME, POPE, ScienceQA, VQA v2, HRBench-8k, XLRS)

60.9GQA Score

7

Mar 11, 2026

GQA, MMB, MME, POPE, SQA, VQAv2, MMMU, SEEDI, VizWiz Standard (test val)

62.3GQA Accuracy

7

Mar 11, 2026

MLLM Evaluation Suite (GQA, MMBench, MME, POPE, ScienceQA, VQAv2, MMMU, SEED-I) LLaVA-NeXT (test)

64.2GQA Accuracy

7

Mar 11, 2026

VLM Evaluation Suite (GQA, MMB, MMBCN, MME, POPE, SQA, VQAv2, VQAText) LLaVA-NEXT-7B (test)

64.2GQA Accuracy

7

Mar 10, 2026

Average across MMB, MMBC, MMstar, MMMU, AI2D

71.2Average Accuracy

7

Feb 26, 2026

Page 9 of 12

Popular datasets

MMBench MMMU MME SEED-Bench MM-Vet

Follow for updates

Join SOTA2 Contact