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. ⚠️ Note: This model routes through Baidu, a Chinese entity - privacy and logging guarantees may be limited.
Added Jun 30, 2025
Context Window
131.1K
Max Output
16.4K
Input Price (Auto)
$0.35/1M
Output Price (Auto)
$1.15/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
15.0
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
14.5
Agentic Index
0.0
GPQA Diamond
Graduate-level scientific reasoning
81.1%
Better than 84% of models compared
HLE
Humanity's Last Exam
3.5%
Better than 5% of models compared
IFBench
Instruction-following benchmark
39.1%
Better than 43% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
0.0%
Better than 3% of models compared
AA-LCR
Long context reasoning evaluation
2.3%
Better than 17% of models compared
CritPt
Research-level physics reasoning
0.0%
Better than 36% of models compared
SciCode
Python programming for scientific computing
31.5%
Better than 56% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
6.1%
Better than 39% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
18.7%
Better than 55% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
67.1%
Better than 82% of models compared
Last updated May 15, 2026, 7:34 PM
Artificial Analysis