Baidu: ERNIE 4.5 300B A47B
Analysis Summary
ERNIE 4.5 300B A47B is Baidu's large mixture-of-experts model, with strong knowledge benchmarks (GPQA 0.811, MMLU Pro 0.776) and reasonable math performance. However, its agentic index sits at just 6.1 and its long-context reliability score is near zero, which are significant gaps for business workflows that depend on multi-step reasoning or document-length tasks.
For businesses, this model is best suited to knowledge retrieval and structured Q&A rather than autonomous agents or long-document analysis. The lack of vision or tool-use support further narrows its applicability. Coding capability is moderate at best, with livecodebench at 0.467 but no dedicated coding index reported.
Pricing is low at $0.28 input and $1.10 output, which offers reasonable cost for lighter workloads. Teams outside Baidu's primary market may find integration and support more limited, so it suits organisations already embedded in that ecosystem rather than those building new pipelines from scratch.
Assessed June 30, 2026
Editorial notes
ERNIE 4.5 300B A47B from Baidu shows strong GPQA and MMLU Pro scores but very weak agentic capability and near-zero long-context reliability, limiting its business utility.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Baidu: ERNIE 4.5 300B A47B compares
Baidu: ERNIE 4.5 300B A47B ranks #247 of 385 AI models we track for overall intelligence, #282 of 293 for agentic tasks. Its 131K-token context window is larger than 59% of the models we list. At $0.28 per million input tokens it is cheaper than 44% of comparable models.
About Baidu: ERNIE 4.5 300B A47B
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..
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Baidu: ERNIE 4.5 300B A47B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
baidu/ernie-4.5-300b-a47b
|
| Provider | baidu |
| Release Date | June 30, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 12,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.28 | $0.000280 |
| Output | $1.10 | $0.001100 |
Leaderboard Categories
External Resources
Frequently asked questions about Baidu: ERNIE 4.5 300B A47B
How much does Baidu: ERNIE 4.5 300B A47B cost?
Baidu: ERNIE 4.5 300B A47B costs $0.28 per million input tokens and $1.10 per million output tokens.
What is the context window of Baidu: ERNIE 4.5 300B A47B?
Baidu: ERNIE 4.5 300B A47B has a context window of 131,072 tokens (131K).
Who created Baidu: ERNIE 4.5 300B A47B?
Baidu: ERNIE 4.5 300B A47B is developed by Baidu and was released on June 30, 2025.
