The AI arena is free today

Open Superagent

Grok-3 Mini vs Grok-4 Heavy

Grok-4 Heavy leads the LLM Stats Score 40.6 to 31.3.

xAI · xAI · Updated for 2026

Which is better?

Grok-4 Heavy leads the overall LLM Stats Score 40.6 to 31.3, ranking #66 overall.

In the 3 individual benchmarks reported for both models, Grok-4 Heavy 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 Grok-3 Mini

  • you want predictable pricing at $0.30/M input and $0.50/M output

Choose Grok-4 Heavy

  • overall performance matters — it scores 40.6 and ranks #66 on LLM Stats
  • you value its reported benchmark strengths — it wins 2 of 3 exact shared results

At a glance

The differences that matter most.

Grok-3 Mini
xAI
Grok-4 Heavy
xAI
Core performance indexes
LLM Stats Score
31.3
#127
40.6
#66
Reasoning
30.9
#128
38.9
#70
Coding
18.6
#122
17.6
#128
Cost, coverage & limits
Benchmark wins
1 of 3
2 of 3
Input price
$0.30 / M
— / M
Output price
$0.50 / M
— / M
Context window
128,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Grok-3 Mini
Grok-4 Heavy
Math
28.3#97
41.5#7
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

4 reported for Grok-3 Mini · 6 for Grok-4 Heavy

3 shared

Grok-3 Mini outperforms in 1 benchmarks (LiveCodeBench), while Grok-4 Heavy is better at 2 benchmarks (AIME 2025, GPQA).

Grok-4 Heavy shows notably better performance in the majority of benchmarks.

Fri Oct 09 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground 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-3 Mini
Input128,000 tokens
Output8,000 tokens
xAI
Grok-4 Heavy
Input- tokens
Output- tokens
Fri Oct 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Grok-3 Mini and Grok-4 Heavy support multimodal inputs.

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

Grok-3 Mini

Text
Images
Audio
Video

Grok-4 Heavy

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-3 Mini

Proprietary

Closed source

Grok-4 Heavy

Proprietary

Closed source

Release Timeline

When each model was launched

Grok-3 Mini was released on 2025-02-17, while Grok-4 Heavy's release date is not specified.

We can confirm Grok-3 Mini's release timeline, but cannot make a direct age comparison without Grok-4 Heavy's release date.

Grok-3 Mini

Feb 17, 2025

1.6 years ago

Grok-4 Heavy

—

Knowledge Cutoff

When training data ends

Grok-3 Mini has a knowledge cutoff of 2024-11-17, while Grok-4 Heavy has a cutoff of 2024-12-31.

Grok-4 Heavy has more recent training data (up to 2024-12-31), making it potentially better informed about events through that date compared to Grok-3 Mini (2024-11-17).

Grok-3 Mini

Nov 2024

Grok-4 Heavy

Dec 2024

1 mo newer

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Grok-3 Mini and Grok-4 Heavy side-by-side, then vote on the output you prefer.

Grok-3 Mini
✓ Preferred
Grok-4 Heavy
Open in Playground

FAQ

Common questions about Grok-3 Mini vs Grok-4 Heavy.

Which is better, Grok-3 Mini or Grok-4 Heavy?

Grok-4 Heavy leads the LLM Stats Score 40.6 to 31.3. Grok-3 Mini is made by xAI and Grok-4 Heavy is made by xAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Grok-3 Mini compare to Grok-4 Heavy in benchmarks?

Grok-3 Mini scores AIME 2024: 95.8%, AIME 2025: 90.8%, GPQA: 84.0%, LiveCodeBench: 80.4%. Grok-4 Heavy scores AIME 2025: 100.0%, HMMT25: 96.7%, GPQA: 88.4%, LiveCodeBench: 79.4%, USAMO25: 61.9%.

What are the context window sizes for Grok-3 Mini and Grok-4 Heavy?

Grok-3 Mini supports 128K tokens and Grok-4 Heavy 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 Grok-3 Mini and Grok-4 Heavy?

Key differences include LLM Stats Score (31.3 vs 40.6). See the full comparison above for benchmark-by-benchmark results.

Related comparisons