Model Comparison

Gemma 3 4B vs Kimi K2-Instruct-0905Which is better in 2026?

Kimi K2-Instruct-0905 significantly outperforms across most benchmarks.

Verdict: Gemma 3 4B vs Kimi K2-Instruct-0905 — which is better?

Gemma 3 4B (by Google) and Kimi K2-Instruct-0905 (by Moonshot AI) 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.

Gemma 3 4B outperforms in 1 benchmarks (IFEval), while Kimi K2-Instruct-0905 is better at 4 benchmarks (GPQA, LiveCodeBench, MMLU-Pro, SimpleQA). Kimi K2-Instruct-0905 significantly outperforms across most benchmarks.

Choose Gemma 3 4B if…

  • you want predictable pricing at $0.02/M input and $0.04/M output

Choose Kimi K2-Instruct-0905 if…

  • you want the strongest raw capability — it leads on 4 of 5 shared benchmarks
  • you want the most recent training data — it shipped Sep 2025

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Gemma 3 4B outperforms in 1 benchmarks (IFEval), while Kimi K2-Instruct-0905 is better at 4 benchmarks (GPQA, LiveCodeBench, MMLU-Pro, SimpleQA).

Kimi K2-Instruct-0905 significantly outperforms across most benchmarks.

Sat Jul 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

996.0B diff

Kimi K2-Instruct-0905 has 996.0B more parameters than Gemma 3 4B, making it 24900.0% larger.

Google
Gemma 3 4B
4.0Bparameters
Moonshot AI
Kimi K2-Instruct-0905
1.0Tparameters
4.0B
Gemma 3 4B
1000.0B
Kimi K2-Instruct-0905

Context Window

Maximum input and output token capacity

Only Gemma 3 4B specifies input context (131,072 tokens). Only Gemma 3 4B specifies output context (131,072 tokens).

Google
Gemma 3 4B
Input131,072 tokens
Output131,072 tokens
Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
Sat Jul 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Gemma 3 4B supports multimodal inputs, whereas Kimi K2-Instruct-0905 does not.

Gemma 3 4B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 3 4B

Text
Images
Audio
Video

Kimi K2-Instruct-0905

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 3 4B is licensed under Gemma, while Kimi K2-Instruct-0905 uses MIT.

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

Gemma 3 4B

Gemma

Open weights

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

Gemma 3 4B was released on 2025-03-12, while Kimi K2-Instruct-0905 was released on 2025-09-05.

Kimi K2-Instruct-0905 is 6 months newer than Gemma 3 4B.

Gemma 3 4B

Mar 12, 2025

1.4 years ago

Kimi K2-Instruct-0905

Sep 5, 2025

10 months ago

5mo newer

Knowledge Cutoff

When training data ends

Gemma 3 4B has a documented knowledge cutoff of 2024-08-01, while Kimi K2-Instruct-0905's cutoff date is not specified.

We can confirm Gemma 3 4B's training data extends to 2024-08-01, but cannot make a direct comparison without Kimi K2-Instruct-0905's cutoff date.

Gemma 3 4B

Aug 2024

Kimi K2-Instruct-0905

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Google
Larger context window (131,072 tokens)
Supports multimodal inputs
Higher IFEval score (90.2% vs 89.8%)
Moonshot AI
Higher GPQA score (75.1% vs 30.8%)
Higher LiveCodeBench score (53.7% vs 12.6%)
Higher MMLU-Pro score (81.1% vs 43.6%)
Higher SimpleQA score (31.0% vs 4.0%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Gemma 3 4B and Kimi K2-Instruct-0905 side-by-side, then vote on the output you prefer.

Gemma 3 4B
✓ Preferred
Kimi K2-Instruct-0905
Open in Playground
AI Model Comparison Table
Feature
Google
Gemma 3 4B
Moonshot AI
Kimi K2-Instruct-0905

FAQ

Common questions about Gemma 3 4B vs Kimi K2-Instruct-0905.

Which is better, Gemma 3 4B or Kimi K2-Instruct-0905?

Kimi K2-Instruct-0905 significantly outperforms across most benchmarks. Gemma 3 4B is made by Google and Kimi K2-Instruct-0905 is made by Moonshot AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Gemma 3 4B compare to Kimi K2-Instruct-0905 in benchmarks?

Gemma 3 4B scores IFEval: 90.2%, GSM8k: 89.2%, DocVQA: 75.8%, MATH: 75.6%, AI2D: 74.8%. Kimi K2-Instruct-0905 scores MATH-500: 97.4%, MMLU-Redux: 92.7%, IFEval: 89.8%, AutoLogi: 89.5%, MMLU: 89.5%.

What are the context window sizes for Gemma 3 4B and Kimi K2-Instruct-0905?

Gemma 3 4B supports 131K tokens and Kimi K2-Instruct-0905 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 Gemma 3 4B and Kimi K2-Instruct-0905?

Key differences include multimodal support (yes vs no), licensing (Gemma vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 3 4B and Kimi K2-Instruct-0905?

Gemma 3 4B is developed by Google and Kimi K2-Instruct-0905 is developed by Moonshot AI.

Related comparisons