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 Tool Use research benchmarks · SOTA2 Research

Multimodal Tool Use

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ReGRPO (default, λval = 0)

67.66Answer Accuracy

33

Jul 1, 2026

33.53Avg@4

16

May 12, 2026

Qwen3.5-35B-A3B

50Avg@4

16

May 12, 2026

LLaVA-Bench Tool Use

89.3Grounding

8

Feb 26, 2026

Popular datasets

LLaVA-Bench GTA MMSearch TIR-Bench

Follow for updates

Join SOTA2 Contact