Baidu: ERNIE 4.5 300B A47B

Baidu: ERNIE 4.5 300B A47B

baidu · Released Jun 30, 2025 Professional
Intelligence #10 / 576
82.0 Our Score
Speed #268 / 271
23.1 tokens / sec
Input #324 / 577
$0.280 per 1M tokens
Output #330 / 577
$1.10 per 1M tokens
Context #233 / 577
131,072 tokens

Analysis Summary

Baidu ERNIE 4.5 300B A47B is a large text-only model from Baidu with benchmark data showing a modest intelligence index of 15 and a coding index of 14.5. Its GPQA score of 0.811 is a bright spot, but agentic capability is very low at 6.1, and long-context reliability is near zero. Instruction following is moderate.

For businesses, this model is not well suited to coding, agentic workflows, or long-document tasks. Its math and science reasoning scores are limited, and the absence of tool use or vision support further restricts its applicability. It may serve narrow structured-output tasks at low cost.

A regional accessibility penalty applies. At $0.28 input and $1.10 output per million tokens, pricing is low, but the capability profile means most business teams will find better options at similar or slightly higher cost.

Assessed June 6, 2026

Editorial notes

Baidu ERNIE 4.5 300B A47B shows limited intelligence and very weak agentic and long-context performance; a regional accessibility penalty applies, and stronger alternatives exist at comparable pricing.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.1Technical1.9Value7.8Content2.3
Intelligence 3.1/10
Technical 1.9/10
Content 2.3/10
Value 7.8/10

How Baidu: ERNIE 4.5 300B A47B compares

Baidu: ERNIE 4.5 300B A47B ranks #235 of 378 AI models we track for overall intelligence, #184 of 315 for coding, #278 of 289 for agentic tasks. Its 131K-token context window is larger than 60% 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..

300B Parameters

Performance Indices

Source: Artificial Analysis

15 Intelligence Index
14.5 Coding Index
6.1 Agentic Index
41.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 81.1% Graduate-level scientific reasoning
HLE 3.5% Humanity's Last Exam
MMLU Pro 77.6% Multi-task language understanding
MATH 500 93.1% Mathematical problem-solving
AIME 49.3% Competition mathematics
AIME 2025 41.3% Competition mathematics (2025)
SciCode 31.5% Scientific computing

Technical

LiveCodeBench 46.7% Live coding evaluation
TerminalBench Hard 6.1% Agentic terminal tasks

Content

IFBench 39.1% Instruction following
LCR 2.3% Long-context reasoning

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.

Compare Models

Model Information

OpenRouter ID baidu/ernie-4.5-300b-a47b
Providerbaidu
Release Date June 30, 2025
Context Length131,072 tokens
Max Completion12,000 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

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).

Is Baidu: ERNIE 4.5 300B A47B good for coding?

On our coding benchmark index, Baidu: ERNIE 4.5 300B A47B ranks #184 of 315 models, placing it in the broader range of the field for code generation and debugging.

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.