The AI arena is free today

Open Superagent

Ministral 3 (3B Base 2512) vs Qwen3 VL 235B A22B Thinking

Qwen3 VL 235B A22B Thinking leads the LLM Stats Score 26.7 to -6.4.

Mistral AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Qwen3 VL 235B A22B Thinking leads the overall LLM Stats Score 26.7 to -6.4, ranking #151 overall.

In the 2 individual benchmarks reported for both models, Qwen3 VL 235B A22B Thinking wins 2; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Ministral 3 (3B Base 2512)

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

Choose Qwen3 VL 235B A22B Thinking

  • overall performance matters — it scores 26.7 and ranks #151 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results

At a glance

The differences that matter most.

Core performance indexes
-6.4
#366
26.7
#151
-6.4
#355
26.9
#145
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
— / M
$0.45 / M
Output price
— / M
$3.49 / M
Context window
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Ministral 3 (3B Base 2512)
Qwen3 VL 235B A22B Thinking
-0.8#299
29.6#82
-1.6#189
31.7#17
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

6 reported for Ministral 3 (3B Base 2512) · 67 for Qwen3 VL 235B A22B Thinking

2 shared

Ministral 3 (3B Base 2512) outperforms in 0 benchmarks, while Qwen3 VL 235B A22B Thinking is better at 2 benchmarks (MMLU, MMLU-Redux).

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

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

233.0B diff

Qwen3 VL 235B A22B Thinking has 233.0B more parameters than Ministral 3 (3B Base 2512), making it 7766.7% larger.

Mistral AI
Ministral 3 (3B Base 2512)
3.0Bparameters
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking
236.0Bparameters
3.0B
Ministral 3 (3B Base 2512)
236.0B
Qwen3 VL 235B A22B Thinking

Context Window

Maximum input and output token capacity

Only Qwen3 VL 235B A22B Thinking specifies input context (262,144 tokens). Only Qwen3 VL 235B A22B Thinking specifies output context (262,144 tokens).

Mistral AI
Ministral 3 (3B Base 2512)
Input- tokens
Output- tokens
Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Thinking
Input262,144 tokens
Output262,144 tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Ministral 3 (3B Base 2512) and Qwen3 VL 235B A22B Thinking support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Ministral 3 (3B Base 2512)

Text
Images
Audio
Video

Qwen3 VL 235B A22B Thinking

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Ministral 3 (3B Base 2512)

Apache 2.0

Open weights

Qwen3 VL 235B A22B Thinking

Apache 2.0

Open weights

Release Timeline

When each model was launched

Ministral 3 (3B Base 2512) was released on 2025-12-04, while Qwen3 VL 235B A22B Thinking was released on 2025-09-22.

Ministral 3 (3B Base 2512) is 2 months newer than Qwen3 VL 235B A22B Thinking.

Ministral 3 (3B Base 2512)

Dec 4, 2025

9 months ago

2mo newer
Qwen3 VL 235B A22B Thinking

Sep 22, 2025

1.0 years ago

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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Ministral 3 (3B Base 2512) and Qwen3 VL 235B A22B Thinking side-by-side, then vote on the output you prefer.

Ministral 3 (3B Base 2512)
✓ Preferred
Qwen3 VL 235B A22B Thinking
Open in Playground

FAQ

Common questions about Ministral 3 (3B Base 2512) vs Qwen3 VL 235B A22B Thinking.

Which is better, Ministral 3 (3B Base 2512) or Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking leads the LLM Stats Score 26.7 to -6.4. Ministral 3 (3B Base 2512) is made by Mistral AI and Qwen3 VL 235B A22B Thinking is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Ministral 3 (3B Base 2512) compare to Qwen3 VL 235B A22B Thinking in benchmarks?

Ministral 3 (3B Base 2512) scores MMLU-Redux: 73.5%, MMLU: 70.7%, Multilingual MMLU: 65.2%, MATH (CoT): 60.1%, TriviaQA: 59.2%. Qwen3 VL 235B A22B Thinking scores ZebraLogic: 97.3%, DocVQAtest: 96.5%, ScreenSpot: 95.4%, CountBench: 93.7%, MMLU-Redux: 93.7%.

What are the context window sizes for Ministral 3 (3B Base 2512) and Qwen3 VL 235B A22B Thinking?

Ministral 3 (3B Base 2512) supports an unknown number of 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 Ministral 3 (3B Base 2512) and Qwen3 VL 235B A22B Thinking?

Key differences include LLM Stats Score (-6.4 vs 26.7). See the full comparison above for benchmark-by-benchmark results.

Who makes Ministral 3 (3B Base 2512) and Qwen3 VL 235B A22B Thinking?

Ministral 3 (3B Base 2512) is developed by Mistral AI and Qwen3 VL 235B A22B Thinking is developed by Alibaba Cloud / Qwen Team.