Share your thoughts, 1 month free Claude Pro on usSee more

Home/Benchmarks

Coding on MAT-Coding

30.6F1 Score

Qwen2.5-VL-3B

Updated 1mo ago

Evaluation Results

Method	Links
Qwen2.5-VL-3B 2025.12		30.6
Qwen2.5-VL-3B 2025.12		16.9

SOTA Paper

Qwen2.5-VL-3B

RLLaVA: An RL-central Framework for Language and Vision Assistants

Dataset

MAT-Coding

Follow for update

@wizwand_team Discord

Related Benchmarks

Math Evaluation on Geometry3K (Accuracy)Counting on CLEVR-Count Grounding on RefCOCO + g Search on MAT-Search

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs