Coder Large vs ERNIE 4.5 21B A3B Thinking (Comparative Analysis)

Compare

Comparative Analysis: Coder Large vs. ERNIE 4.5 21B A3B Thinking

Want to try out these models side by side?Try Galaxy.ai for free

Overview

Coder Large was released 5 months before ERNIE 4.5 21B A3B Thinking.

	Coder Large	ERNIE 4.5 21B A3B Thinking
Model Provider The organization behind this AI's development	Arcee AI	Baidu
Input Context Window Maximum input tokens this model can process at once	32.8K tokens	131.1K tokens
Output Token Limit Maximum output tokens this model can generate at once	Not specified tokens	65.5K tokens
Release Date When this model first became publicly available	May 5, 2025 6 months ago May 5th, 2025	October 9, 2025 1 month ago October 9th, 2025

Capabilities & Features

Compare supported features, modalities, and advanced capabilities

	Coder Large	ERNIE 4.5 21B A3B Thinking
Input Types Supported input formats	📝Text	📝Text
Output Types Supported output formats	📝Text	📝Text
Tokenizer Text encoding system	Other	Other
Key Features Advanced capabilities	Function CallingStructured OutputReasoning ModeContent Moderation	Function CallingStructured Output✓Reasoning ModeContent Moderation
Open Source Model availability	Proprietary	Available on HuggingFace →

Pricing

Coder Large is roughly 7.1x more expensive compared to ERNIE 4.5 21B A3B Thinking for input tokens and roughly 2.9x more expensive for output tokens.

	Coder Large	ERNIE 4.5 21B A3B Thinking
Input Token Cost Cost per million input tokens	$0.50 per million tokens	$0.07 per million tokens
Output Token Cost Cost per million outut tokens	$0.80 per million tokens	$0.28 per million tokens

Benchmarks

Compare relevant benchmarks between Coder Large and ERNIE 4.5 21B A3B Thinking.

	Coder Large	ERNIE 4.5 21B A3B Thinking
MMLU Measures knowledge across 57 subjects like law, math, history, and science	Benchmark not available.	Benchmark not available.
MMMU Measures understanding of combined text and images across various domains	Benchmark not available.	Benchmark not available.
HellaSwag Measures common sense reasoning by having models complete sentences about everyday situations	Benchmark not available.	Benchmark not available.

At a Glance

Quick overview of what makes Coder Large and ERNIE 4.5 21B A3B Thinking unique.

Coder Large by Arcee AI is a text-based AI model. It can handle standard conversations with its 32.8K token context window. Reasonably priced at $0.50/M input and $0.80/M output tokens. Released May 5th, 2025.

ERNIE 4.5 21B A3B Thinking by Baidu offers advanced reasoning. It can handle standard conversations with its 131.1K token context window. Very affordable at $0.07/M input and $0.28/M output tokens. Released October 9th, 2025.