The AI arena is free today

Open Superagent

Gemma 3 4B vs Kimi K2-Instruct-0905

Kimi K2-Instruct-0905 leads the LLM Stats Score 20.8 to -2.4.

Google · Moonshot AI · Updated for 2026

Which is better?

Kimi K2-Instruct-0905 leads the overall LLM Stats Score 20.8 to -2.4, ranking #235 overall.

In the 5 individual benchmarks reported for both models, Kimi K2-Instruct-0905 wins 4; 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 Gemma 3 4B

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

Choose Kimi K2-Instruct-0905

  • overall performance matters — it scores 20.8 and ranks #235 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 5 exact shared results
  • you want the most recent training data — it shipped Sep 2025

At a glance

The differences that matter most.

Core performance indexes
-2.4
#388
20.8
#235
-3.5
#384
21.1
#221
-4.5
#301
9.6
#210
Cost, coverage & limits
Benchmark wins
1 of 5
4 of 5
Input price
$0.02 / M
— / M
Output price
$0.04 / M
— / M
Context window
131,072
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 3 4B
Kimi K2-Instruct-0905
4.9#301
21.4#164
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

26 reported for Gemma 3 4B · 29 for Kimi K2-Instruct-0905

5 shared

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.

Tue Nov 17 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

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
Tue Nov 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

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

1.7 years ago

Kimi K2-Instruct-0905

Sep 5, 2025

1.2 years 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?

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

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 leads the LLM Stats Score 20.8 to -2.4. 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 capability indexes, individual benchmarks, pricing, and limits 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 LLM Stats Score (-2.4 vs 20.8), 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.