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

Paired-prompt evaluation research benchmarks · SOTA2 Research

Paired-prompt evaluation

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

LLaVA-NeXT-Vicuna-7B

58.81Simple Accuracy

2

Feb 26, 2026

LLaVA-NeXT-Vicuna-7B

64.56Simple Accuracy

2

Feb 26, 2026

LLaVA-NeXT-Vicuna-7B

67.81Simple Accuracy

2

Feb 26, 2026

LLaVA-NeXT-Vicuna-7B

75.7Simple Accuracy

2

Feb 26, 2026

LLaVA-NeXT-Vicuna-7B

52.89Simple Accuracy

2

Feb 26, 2026

LLaVA-NeXT-Vicuna-7B

90.67Simple Accuracy

2

Feb 26, 2026

Popular datasets

MME HallusionBench Winoground SugarCrepe NaturalBench

Follow for updates

Join SOTA2 Contact