Model Comparison

Gemini 3.1 Pro vs ERNIE 4.5Which is better in 2026?

Gemini 3.1 Pro significantly outperforms across most benchmarks. ERNIE 4.5 is 4.3x cheaper per token.

Verdict: Gemini 3.1 Pro vs ERNIE 4.5 — which is better?

Gemini 3.1 Pro (by Google) and ERNIE 4.5 (by Baidu) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Gemini 3.1 Pro outperforms in 1 benchmarks (GPQA), while ERNIE 4.5 is better at 0 benchmarks. Gemini 3.1 Pro significantly outperforms across most benchmarks.

On price, ERNIE 4.5 is roughly 4.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Gemini 3.1 Pro also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

Choose Gemini 3.1 Pro if…

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Feb 2026

Choose ERNIE 4.5 if…

  • cost matters — it's about 4.3x cheaper per token
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Gemini 3.1 Pro outperforms in 1 benchmarks (GPQA), while ERNIE 4.5 is better at 0 benchmarks.

Gemini 3.1 Pro significantly outperforms across most benchmarks.

Tue Jun 23 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

ERNIE 4.5 costs less

For input processing, Gemini 3.1 Pro ($2.50/1M tokens) is 6.3x more expensive than ERNIE 4.5 ($0.40/1M tokens).

For output processing, Gemini 3.1 Pro ($15.00/1M tokens) is 3.8x more expensive than ERNIE 4.5 ($4.00/1M tokens).

In conclusion, Gemini 3.1 Pro is more expensive than ERNIE 4.5.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Jun 23 2026 • llm-stats.com
Google
Gemini 3.1 Pro
Input tokens$2.50
Output tokens$15.00
Best providerGoogle
Baidu
ERNIE 4.5
Input tokens$0.40
Output tokens$4.00
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Gemini 3.1 Pro accepts 1,048,576 input tokens compared to ERNIE 4.5's 128,000 tokens. Both models can generate responses up to 65,536 tokens.

Google
Gemini 3.1 Pro
Input1,048,576 tokens
Output65,536 tokens
Baidu
ERNIE 4.5
Input128,000 tokens
Output65,536 tokens
Tue Jun 23 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemini 3.1 Pro supports multimodal inputs, whereas ERNIE 4.5 does not.

Gemini 3.1 Pro can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemini 3.1 Pro

Text
Images
Audio
Video

ERNIE 4.5

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Gemini 3.1 Pro

Proprietary

Closed source

ERNIE 4.5

Proprietary

Closed source

Release Timeline

When each model was launched

Gemini 3.1 Pro was released on 2026-02-19, while ERNIE 4.5 was released on 2025-06-25.

Gemini 3.1 Pro is 8 months newer than ERNIE 4.5.

Gemini 3.1 Pro

Feb 19, 2026

4 months ago

7mo newer
ERNIE 4.5

Jun 25, 2025

12 months ago

Knowledge Cutoff

When training data ends

Gemini 3.1 Pro has a documented knowledge cutoff of 2025-01-31, while ERNIE 4.5's cutoff date is not specified.

We can confirm Gemini 3.1 Pro's training data extends to 2025-01-31, but cannot make a direct comparison without ERNIE 4.5's cutoff date.

Gemini 3.1 Pro

Jan 2025

ERNIE 4.5

—

Provider Availability

Gemini 3.1 Pro is available from Google. ERNIE 4.5 is available from Novita.

Gemini 3.1 Pro

google logo
Google
Input Price:Input: $2.50/1MOutput Price:Output: $15.00/1M

ERNIE 4.5

novita logo
Novita
Input Price:Input: $0.40/1MOutput Price:Output: $4.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (1,048,576 tokens)
Supports multimodal inputs
Higher GPQA score (94.3% vs 74.0%)
Baidu
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Google
Gemini 3.1 Pro
Baidu
ERNIE 4.5

FAQ

Common questions about Gemini 3.1 Pro vs ERNIE 4.5.

Which is better, Gemini 3.1 Pro or ERNIE 4.5?

Gemini 3.1 Pro significantly outperforms across most benchmarks. Gemini 3.1 Pro is made by Google and ERNIE 4.5 is made by Baidu. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemini 3.1 Pro compare to ERNIE 4.5 in benchmarks?

Gemini 3.1 Pro scores t2-bench: 99.3%, LiveCodeBench Pro: 96.2%, GPQA: 94.3%, MMMLU: 92.6%, BrowseComp: 85.9%. ERNIE 4.5 scores GPQA: 74.0%, ARC-E: 60.7%, PIQA: 55.2%, Winogrande: 51.3%, CLUEWSC: 48.6%.

Is Gemini 3.1 Pro cheaper than ERNIE 4.5?

ERNIE 4.5 is 6.3x cheaper for input tokens. Gemini 3.1 Pro costs $2.50/M input and $15.00/M output via google. ERNIE 4.5 costs $0.40/M input and $4.00/M output via novita.

What are the context window sizes for Gemini 3.1 Pro and ERNIE 4.5?

Gemini 3.1 Pro supports 1.0M tokens and ERNIE 4.5 supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemini 3.1 Pro and ERNIE 4.5?

Key differences include context window (1.0M vs 128K), input pricing ($2.50 vs $0.40/M), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 3.1 Pro and ERNIE 4.5?

Gemini 3.1 Pro is developed by Google and ERNIE 4.5 is developed by Baidu.

Related comparisons