Baidu: ERNIE 4.5 300B A47B
Baidu's ERNIE 4.5 300B A47B has benchmark data but scores very low across intelligence, coding, and agentic dimensions, making it unsuitable for demanding business tasks despite its reasonable pricing.
Assessment date: March 12, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in both English and Chinese. Optimized for high-throughput inference and efficient scaling, it uses a heterogeneous MoE structure with advanced routing and quantization strategies, including FP8 and 2-bit formats. This version is fine-tuned for language-only tasks and supports reasoning, tool parameters, and extended context lengths up to 131k tokens. Suitable for general-purpose LLM applications with high reasoning and throughput demands.
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
| Parameters | 300B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.28 | $0.000280 |
| Output | $1.10 | $0.001100 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
