The AI arena is free today

Open Superagent

Grok-2 mini vs Grok-3 Mini

Grok-3 Mini significantly outperforms across most benchmarks.

xAI · xAI · Updated for 2026

Which is better?

Grok-2 mini outperforms in 0 benchmarks, while Grok-3 Mini is better at 1 benchmark (GPQA). Grok-3 Mini significantly outperforms across most benchmarks.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Grok-2 mini

  • you are already invested in the xAI ecosystem

Choose Grok-3 Mini

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • you want the most recent training data — it shipped Feb 2025

At a glance

The differences that matter most.

Grok-2 mini
xAI
Grok-3 Mini
xAI
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.30 / M
Output price
— / M
$0.50 / M
Context window
—
128,000
Released
Aug 2024
Feb 2025
License
Proprietary
Proprietary

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Grok-2 mini outperforms in 0 benchmarks, while Grok-3 Mini is better at 1 benchmark (GPQA).

Grok-3 Mini significantly outperforms across most benchmarks.

Wed Aug 26 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Context Window

Maximum input and output token capacity

Only Grok-3 Mini specifies input context (128,000 tokens). Only Grok-3 Mini specifies output context (8,000 tokens).

xAI
Grok-2 mini
Input- tokens
Output- tokens
xAI
Grok-3 Mini
Input128,000 tokens
Output8,000 tokens
Wed Aug 26 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Grok-2 mini and Grok-3 Mini support multimodal inputs.

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

Grok-2 mini

Text
Images
Audio
Video

Grok-3 Mini

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.

Grok-2 mini

Proprietary

Closed source

Grok-3 Mini

Proprietary

Closed source

Release Timeline

When each model was launched

Grok-2 mini was released on 2024-08-13, while Grok-3 Mini was released on 2025-02-17.

Grok-3 Mini is 6 months newer than Grok-2 mini.

Grok-2 mini

Aug 13, 2024

2.0 years ago

Grok-3 Mini

Feb 17, 2025

1.5 years ago

6mo newer

Knowledge Cutoff

When training data ends

Grok-3 Mini has a documented knowledge cutoff of 2024-11-17, while Grok-2 mini's cutoff date is not specified.

We can confirm Grok-3 Mini's training data extends to 2024-11-17, but cannot make a direct comparison without Grok-2 mini's cutoff date.

Grok-2 mini

—

Grok-3 Mini

Nov 2024

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Grok-2 mini and Grok-3 Mini side-by-side, then vote on the output you prefer.

Grok-2 mini
✓ Preferred
Grok-3 Mini
Open in Playground

FAQ

Common questions about Grok-2 mini vs Grok-3 Mini.

Which is better, Grok-2 mini or Grok-3 Mini?

Grok-3 Mini significantly outperforms across most benchmarks. Grok-2 mini is made by xAI and Grok-3 Mini is made by xAI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Grok-2 mini compare to Grok-3 Mini in benchmarks?

Grok-2 mini scores DocVQA: 93.2%, MMLU: 86.2%, HumanEval: 85.7%, MATH: 73.0%, MMLU-Pro: 72.0%. Grok-3 Mini scores AIME 2024: 95.8%, AIME 2025: 90.8%, GPQA: 84.0%, LiveCodeBench: 80.4%.

What are the context window sizes for Grok-2 mini and Grok-3 Mini?

Grok-2 mini supports an unknown number of tokens and Grok-3 Mini supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

Related comparisons