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 7 · SOTA2 Research

Multimodal Understanding

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MM-Vet benign queries

54.5Recognition Score

12

Mar 10, 2026

R1-OneVision 1.0 (test)

Gemini-2.0-Flash

59.1Average Score

12

Mar 4, 2026

MM-Bench (MMB) en (dev)

85Accuracy

12

Mar 4, 2026

SeedBench image

76.7Score

12

Feb 27, 2026

CCB (Chinese Comprehensive Benchmark)

75.3CCB Score

12

Feb 26, 2026

MMStar (5% Forget Set)

49.27Average Score

12

Feb 26, 2026

MM-Vet (5% Forget Set)

43.9Average Score

12

Feb 26, 2026

Aggregated Multimodal Suite

73.29Average Accuracy

11

Jul 7, 2026

58.6Accuracy

11

Jul 7, 2026

LaViDa-O + RL (Global + Factorized)

64.25Accuracy

11

Jun 16, 2026

64MMBench Score

11

Jun 2, 2026

77.6ACC

11

Jun 23, 2026

33.85Avg_mul

11

May 14, 2026

57.5Score

11

Apr 7, 2026

1,845MME Score

10

May 22, 2026

Vision-Language Benchmark Suite MMMU, MathVista, MMBEn, MMBCn, MMStar, HallBench, AI2D, OCRBench

63.9MMMU Score

10

May 12, 2026

Understanding Benchmarks Aggregate

100Overall Score

10

Apr 15, 2026

DeepSeek-VL2 Evaluation Suite

72.68Average Score

10

Mar 23, 2026

81Score

10

Mar 23, 2026

Real-world LVLM Benchmarks Aggregate 80% (test)

81.42MCQ Accuracy

10

Mar 10, 2026

ViLP 80% (test)

58.06Accuracy

10

Mar 10, 2026

MMStar 80% (test)

60.08Accuracy

10

Mar 10, 2026

CCBench 80% (test)

73.96Accuracy

10

Mar 10, 2026

87.89Accuracy

10

Mar 10, 2026

MMBench E 80% (dev test)

86.67Accuracy

10

Mar 10, 2026

Page 7 of 12

Popular datasets

MMBench MMMU MME SEED-Bench MM-Vet

Follow for updates

Join SOTA2 Contact