Model Comparison

ERNIE 4.5 vs Qwen3 VL 235B A22B ThinkingWhich is better in 2026?

Qwen3 VL 235B A22B Thinking significantly outperforms across most benchmarks. Qwen3 VL 235B A22B Thinking is 1.1x cheaper per token.

Verdict: ERNIE 4.5 vs Qwen3 VL 235B A22B Thinking — which is better?

ERNIE 4.5 (by Baidu) and Qwen3 VL 235B A22B Thinking (by Alibaba Cloud / Qwen Team) 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 0 benchmarks, while Qwen3 VL 235B A22B Thinking is better at 4 benchmarks (MMLU, MMLU-Pro, MMLU-Redux, SimpleQA). Qwen3 VL 235B A22B Thinking significantly outperforms across most benchmarks.

On price, Qwen3 VL 235B A22B Thinking is roughly 1.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Qwen3 VL 235B A22B Thinking also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Choose ERNIE 4.5 if…

  • you want predictable pricing at $0.40/M input and $4.00/M output

Choose Qwen3 VL 235B A22B Thinking if…

  • you want the strongest raw capability — it leads on 4 of 4 shared benchmarks
  • cost matters — it's about 1.1x cheaper per token
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Sep 2025
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

ERNIE 4.5 outperforms in 0 benchmarks, while Qwen3 VL 235B A22B Thinking is better at 4 benchmarks (MMLU, MMLU-Pro, MMLU-Redux, SimpleQA).

Qwen3 VL 235B A22B Thinking significantly outperforms across most benchmarks.

Sun Jun 07 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Qwen3 VL 235B A22B Thinking costs less

For input processing, ERNIE 4.5 ($0.40/1M tokens) is 1.1x cheaper than Qwen3 VL 235B A22B Thinking ($0.45/1M tokens).

For output processing, ERNIE 4.5 ($4.00/1M tokens) is 1.1x more expensive than Qwen3 VL 235B A22B Thinking ($3.49/1M tokens).

In conclusion, ERNIE 4.5 is more expensive than Qwen3 VL 235B A22B Thinking.*

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

Lowest available price from all providers
Sun Jun 07 2026 • llm-stats.com
Baidu
ERNIE 4.5
Input tokens$0.40
Output tokens$4.00
Best providerNovita
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking
Input tokens$0.45
Output tokens$3.49
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

215.0B diff

Qwen3 VL 235B A22B Thinking has 215.0B more parameters than ERNIE 4.5, making it 1023.8% larger.

Baidu
ERNIE 4.5
21.0Bparameters
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking
236.0Bparameters
21.0B
ERNIE 4.5
236.0B
Qwen3 VL 235B A22B Thinking

Context Window

Maximum input and output token capacity

Qwen3 VL 235B A22B Thinking accepts 262,144 input tokens compared to ERNIE 4.5's 128,000 tokens. Qwen3 VL 235B A22B Thinking can generate longer responses up to 262,144 tokens, while ERNIE 4.5 is limited to 65,536 tokens.

Baidu
ERNIE 4.5
Input128,000 tokens
Output65,536 tokens
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking
Input262,144 tokens
Output262,144 tokens
Sun Jun 07 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Qwen3 VL 235B A22B Thinking supports multimodal inputs, whereas ERNIE 4.5 does not.

Qwen3 VL 235B A22B Thinking can handle both text and other forms of data like images, making it suitable for multimodal applications.

ERNIE 4.5

Text
Images
Audio
Video

Qwen3 VL 235B A22B Thinking

Text
Images
Audio
Video

License

Usage and distribution terms

ERNIE 4.5 is licensed under a proprietary license, while Qwen3 VL 235B A22B Thinking uses Apache 2.0.

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

ERNIE 4.5

Proprietary

Closed source

Qwen3 VL 235B A22B Thinking

Apache 2.0

Open weights

Release Timeline

When each model was launched

ERNIE 4.5 was released on 2025-06-25, while Qwen3 VL 235B A22B Thinking was released on 2025-09-22.

Qwen3 VL 235B A22B Thinking is 3 months newer than ERNIE 4.5.

ERNIE 4.5

Jun 25, 2025

11 months ago

Qwen3 VL 235B A22B Thinking

Sep 22, 2025

8 months ago

2mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

ERNIE 4.5 is available from Novita. Qwen3 VL 235B A22B Thinking is available from DeepInfra, Novita.

ERNIE 4.5

novita logo
Novita
Input Price:Input: $0.40/1MOutput Price:Output: $4.00/1M

Qwen3 VL 235B A22B Thinking

deepinfra logo
Deepinfra
Input Price:Input: $0.45/1MOutput Price:Output: $3.49/1M
novita logo
Novita
Input Price:Input: $0.98/1MOutput Price:Output: $3.95/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Less expensive input tokens
Larger context window (262,144 tokens)
Supports multimodal inputs
Less expensive output tokens
Has open weights
Higher MMLU score (90.6% vs 41.9%)
Higher MMLU-Pro score (83.8% vs 16.0%)
Higher MMLU-Redux score (93.7% vs 43.2%)
Higher SimpleQA score (44.4% vs 1.8%)

Detailed Comparison

AI Model Comparison Table
Feature
Baidu
ERNIE 4.5
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking

FAQ

Common questions about ERNIE 4.5 vs Qwen3 VL 235B A22B Thinking.

Which is better, ERNIE 4.5 or Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking significantly outperforms across most benchmarks. ERNIE 4.5 is made by Baidu and Qwen3 VL 235B A22B Thinking is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does ERNIE 4.5 compare to Qwen3 VL 235B A22B Thinking in benchmarks?

ERNIE 4.5 scores GPQA: 74.0%, ARC-E: 60.7%, PIQA: 55.2%, Winogrande: 51.3%, CLUEWSC: 48.6%. Qwen3 VL 235B A22B Thinking scores ZebraLogic: 97.3%, DocVQAtest: 96.5%, ScreenSpot: 95.4%, CountBench: 93.7%, MMLU-Redux: 93.7%.

Is ERNIE 4.5 cheaper than Qwen3 VL 235B A22B Thinking?

ERNIE 4.5 is 1.1x cheaper for input tokens. ERNIE 4.5 costs $0.40/M input and $4.00/M output via novita. Qwen3 VL 235B A22B Thinking costs $0.45/M input and $3.49/M output via deepinfra.

What are the context window sizes for ERNIE 4.5 and Qwen3 VL 235B A22B Thinking?

ERNIE 4.5 supports 128K tokens and Qwen3 VL 235B A22B Thinking supports 262K 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 Qwen3 VL 235B A22B Thinking?

Key differences include context window (128K vs 262K), input pricing ($0.40 vs $0.45/M), multimodal support (no vs yes), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes ERNIE 4.5 and Qwen3 VL 235B A22B Thinking?

ERNIE 4.5 is developed by Baidu and Qwen3 VL 235B A22B Thinking is developed by Alibaba Cloud / Qwen Team.