Baidu debuted two models: a lightweight, open-weights, vision-language model and a giant, proprietary, multimodal model built to take on U.S. competitors.
Ernie-4.5-VL-28B-A3B-Thinking: Baidu’s new open-weights model is based on the earlier Ernie-4.5-21B-A3B Thinking, a text-only MoE reasoning model, plus a 7 billion-parameter vision encoder to process images.It outperforms comparable and larger models on visual reasoning tasks. It can extract on-screen text and analyze videos across time, and it can call tools to zoom in on image details and search for related images.
- Input/output: Text, image, video in (up to 128,000 tokens); text out
- Architecture: Mixture-of-experts (MoE) transformer (28 billion parameters total, 3 billion active per token), 21 billion-parameter language decoder/encoder.
- Training: The authors used vision-language reasoning examples during mid-training, an emerging phase that typically uses mid-size datasets to sharpen distinct skills or impart specific domains prior to fine-tuning. In addition, they fine-tune via reinforcement learning (RL) with multimodal data. Because MoE architectures can become unstable during RL, the team used a combination of GSPO and IcePop to stabilize the fine-tuning.
- Features: Tool use, reasoning
- Performance: Ernie-4.5-VL-28B-A3B-Thinking competes with larger proprietary models on document understanding tasks despite activating only 3 billion parameters, Baidu said. For instance, on ChartQA (chart interpretation), Ernie-4.5-VL-28B-A3B-Thinking reached 87.1 percent accuracy, outperforming Gemini 2.5 Pro (76.3 percent) and GPT-5 set to high reasoning (78.2 percent). On OCRBench (text recognition in images), it achieved 858, ahead of GPT-5 set to high reasoning (810) but trailing Gemini 2.5 Pro (866).
- Availability: Weights free for noncommercial and commercial uses under Apache 2.0 license via HuggingFace. API $0.14/$0.56 per million input/output tokens via Baidu Qianfan.
- Undisclosed: Output size limit, training data, reward models
Ernie-5.0: Baidu describes Ernie-5.0’s approach as natively multimodal, meaning it was trained on text, images, audio, and video together rather than fusing different media encoders after training or routing inputs to specialized models. It performs comparably to the similarly multimodal Google Gemini 2.5 or OpenAI GPT-5, according to Baidu.
- Input/output: Text, image, audio, and video in (up to 128,000 tokens); text, image, audio, video out (up to 64,000 tokens)
- Architecture: Mixture-of-experts (MoE) transformer (2.4 trillion parameters total, less than 72 billion active per token)
- Features: Vision-language-audio understanding, reasoning, agentic planning, tool use
- Performance: In Baidu’s tests of multimodal reasoning, document understanding, and visual question-answering, the company reports that Ernie-5.0 matched or exceeded OpenAI GPT-5 set to high reasoning and Google Gemini 2.5 Pro. For instance, on OCRBench (document comprehension), DocVQA (document comprehension), and ChartQA (structured data reasoning), Baidu Ernie-5.0 achieved top scores. On MM-AU (multimodal audio understanding) and TUT2017 (acoustic scene classification), it demonstrated competitive performance, Baidu said without publishing specific metrics.
- Availability: Free web interface, API $0.85/$3.40 per million input/output tokens via Baidu Qianfan
- Undisclosed: Training data, training methods
Yes, but: Shortly after Ernie-5.0's launch, a developer reported that the model repeatedly called tools even after instruction not to. Baidu acknowledged the issue and said it was fixing it.
Why it matters: Ernie-4.5-VL-28B-A3B-Thinking offers top visual reasoning at the fraction of the cost of competing models, and more flexibility for fine-tuning and other commercial customizations. However, the long-awaited Ernie 5.0 appears to fall short of expectations. It matches top models on some visual tasks but stops short of the forefront (including Qwen3-Max and Kimi-K2-Thinking) on leaderboards like LM Arena. Pretraining on text, images, video, and audio together is a relatively fresh approach that could simplify current systems that piece together different encoders and decoders for different media types.
We’re thinking: Ernie-5.0 may outperform Gemini 2.5 and GPT-5, but Google and OpenAI have already moved on to Gemini 3 and GPT-5.1!