Model Comparison

ERNIE 4.5 vs Phi 4 Reasoning PlusWhich is better in 2026?

Phi 4 Reasoning Plus shows notably better performance in the majority of benchmarks.

Verdict: ERNIE 4.5 vs Phi 4 Reasoning Plus — which is better?

ERNIE 4.5 (by Baidu) and Phi 4 Reasoning Plus (by Microsoft) 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.

ERNIE 4.5 outperforms in 1 benchmarks (GPQA), while Phi 4 Reasoning Plus is better at 2 benchmarks (HumanEval+, MMLU-Pro). Phi 4 Reasoning Plus shows notably better performance in the majority of benchmarks.

Choose ERNIE 4.5 if…

  • you want the most recent training data — it shipped Jun 2025

Choose Phi 4 Reasoning Plus if…

  • you want the strongest raw capability — it leads on 2 of 3 shared benchmarks
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

ERNIE 4.5 outperforms in 1 benchmarks (GPQA), while Phi 4 Reasoning Plus is better at 2 benchmarks (HumanEval+, MMLU-Pro).

Phi 4 Reasoning Plus shows notably better performance in the majority of benchmarks.

Tue Jul 28 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

7.0B diff

ERNIE 4.5 has 7.0B more parameters than Phi 4 Reasoning Plus, making it 50.0% larger.

Baidu
ERNIE 4.5
21.0Bparameters
Microsoft
Phi 4 Reasoning Plus
14.0Bparameters
21.0B
ERNIE 4.5
14.0B
Phi 4 Reasoning Plus

Context Window

Maximum input and output token capacity

Only ERNIE 4.5 specifies input context (128,000 tokens). Only ERNIE 4.5 specifies output context (65,536 tokens).

Baidu
ERNIE 4.5
Input128,000 tokens
Output65,536 tokens
Microsoft
Phi 4 Reasoning Plus
Input- tokens
Output- tokens
Tue Jul 28 2026 • llm-stats.com

License

Usage and distribution terms

ERNIE 4.5 is licensed under a proprietary license, while Phi 4 Reasoning Plus uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

ERNIE 4.5

Proprietary

Closed source

Phi 4 Reasoning Plus

MIT

Open weights

Release Timeline

When each model was launched

ERNIE 4.5 was released on 2025-06-25, while Phi 4 Reasoning Plus was released on 2025-04-30.

ERNIE 4.5 is 2 months newer than Phi 4 Reasoning Plus.

ERNIE 4.5

Jun 25, 2025

1.1 years ago

1mo newer
Phi 4 Reasoning Plus

Apr 30, 2025

1.2 years ago

Knowledge Cutoff

When training data ends

Phi 4 Reasoning Plus has a documented knowledge cutoff of 2025-03-01, while ERNIE 4.5's cutoff date is not specified.

We can confirm Phi 4 Reasoning Plus's training data extends to 2025-03-01, but cannot make a direct comparison without ERNIE 4.5's cutoff date.

ERNIE 4.5

Phi 4 Reasoning Plus

Mar 2025

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Larger context window (128,000 tokens)
Higher GPQA score (74.0% vs 68.9%)
Has open weights
Higher HumanEval+ score (92.3% vs 25.0%)
Higher MMLU-Pro score (76.0% vs 16.0%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against ERNIE 4.5 and Phi 4 Reasoning Plus side-by-side, then vote on the output you prefer.

ERNIE 4.5
✓ Preferred
Phi 4 Reasoning Plus
Open in Playground
AI Model Comparison Table
Feature
Baidu
ERNIE 4.5
Microsoft
Phi 4 Reasoning Plus

FAQ

Common questions about ERNIE 4.5 vs Phi 4 Reasoning Plus.

Which is better, ERNIE 4.5 or Phi 4 Reasoning Plus?

Phi 4 Reasoning Plus shows notably better performance in the majority of benchmarks. ERNIE 4.5 is made by Baidu and Phi 4 Reasoning Plus is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does ERNIE 4.5 compare to Phi 4 Reasoning Plus in benchmarks?

ERNIE 4.5 scores GPQA: 74.0%, ARC-E: 60.7%, PIQA: 55.2%, Winogrande: 51.3%, CLUEWSC: 48.6%. Phi 4 Reasoning Plus scores FlenQA: 97.9%, HumanEval+: 92.3%, IFEval: 84.9%, OmniMath: 81.9%, AIME 2024: 81.3%.

What are the context window sizes for ERNIE 4.5 and Phi 4 Reasoning Plus?

ERNIE 4.5 supports 128K tokens and Phi 4 Reasoning Plus supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between ERNIE 4.5 and Phi 4 Reasoning Plus?

Key differences include licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes ERNIE 4.5 and Phi 4 Reasoning Plus?

ERNIE 4.5 is developed by Baidu and Phi 4 Reasoning Plus is developed by Microsoft.