Skip to content

ERNIE 4.5 VL Thinking

Released 2025-09 · reasoning · 128K tokens · 0 benchmarks

Editorial notes

VL multimodal con razonamiento profundo. MathVista 82.5, ChartQA 87.1. Supera GPT-5-High en tests visuales.

Spec sheet

Company
Baidu
Country
CN
Type
reasoning
Release
2025-09
Context
128K tokens
License
proprietary
Slug
ernie-4-5-vl-thinking
No scores published for this model. The editorial notes have additional context.
Cite this model
BibTeX · APA

BibTeX

@misc{frontier-ernie-4-5-vl-thinking,
  title  = {ERNIE 4.5 VL Thinking},
  author = {{Baidu}},
  year   = {2025},
  note   = {Frontier Benchmarks AI atlas. Accessed 2026-05-08},
  url    = {https://frontierbenchmarks.com/models/ernie-4-5-vl-thinking}
}

APA

Baidu (2025). ERNIE 4.5 VL Thinking [Large language model]. Frontier Benchmarks AI. Retrieved 2026-05-08, from https://frontierbenchmarks.com/models/ernie-4-5-vl-thinking

Citation reflects the atlas page, not the original model paper. For the paper, see the "Resources" section above.