The AI arena is free today

Open Superagent

Gemma 4 26B-A4B vs Kimi K2 0905

Gemma 4 26B-A4B leads the LLM Stats Score 28.9 to 21.2. Gemma 4 26B-A4B is 7.8x cheaper per token.

Google · Moonshot AI · Updated for 2026

Which is better?

Gemma 4 26B-A4B leads the overall LLM Stats Score 28.9 to 21.2, ranking #171 overall.

In the 2 individual benchmarks reported for both models, Gemma 4 26B-A4B wins 2; this is a narrower head-to-head signal than the composite indexes.

On price, Gemma 4 26B-A4B is roughly 7.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose Gemma 4 26B-A4B

  • overall performance matters — it scores 28.9 and ranks #171 on LLM Stats
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • cost matters — it's about 7.8x cheaper per token
  • you want the most recent training data — it shipped Apr 2026
  • you need open weights you can self-host or fine-tune

Choose Kimi K2 0905

  • you want predictable pricing at $0.60/M input and $2.50/M output

At a glance

The differences that matter most.

Core performance indexes
28.9
#171
21.2
#229
28.5
#164
21.4
#218
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
$0.07 / M
$0.60 / M
Output price
$0.34 / M
$2.50 / M
Context window
262,144
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 4 26B-A4B
Kimi K2 0905
25.1#127
24.3#134
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for Gemma 4 26B-A4B · 6 for Kimi K2 0905

2 shared

Gemma 4 26B-A4B outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Kimi K2 0905 is better at 0 benchmarks.

Gemma 4 26B-A4B significantly outperforms across most benchmarks.

Tue Nov 17 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Gemma 4 26B-A4B costs less

For input processing, Gemma 4 26B-A4B ($0.07/1M tokens) is 8.6x cheaper than Kimi K2 0905 ($0.60/1M tokens).

For output processing, Gemma 4 26B-A4B ($0.34/1M tokens) is 7.4x cheaper than Kimi K2 0905 ($2.50/1M tokens).

In conclusion, Kimi K2 0905 is more expensive than Gemma 4 26B-A4B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Nov 17 2026 • llm-stats.com
Google
Gemma 4 26B-A4B
Input tokens$0.07
Output tokens$0.34
Best providerDeepinfra
Moonshot AI
Kimi K2 0905
Input tokens$0.60
Output tokens$2.50
Best providerNovita
Notice missing or incorrect data?

Model Size

Parameter count comparison

974.8B diff

Kimi K2 0905 has 974.8B more parameters than Gemma 4 26B-A4B, making it 3868.3% larger.

Google
Gemma 4 26B-A4B
25.2Bparameters
Moonshot AI
Kimi K2 0905
1.0Tparameters
25.2B
Gemma 4 26B-A4B
1000.0B
Kimi K2 0905

Context Window

Maximum input and output token capacity

Both models have the same input context window of 262,144 tokens. Both models can generate responses up to 262,144 tokens.

Google
Gemma 4 26B-A4B
Input262,144 tokens
Output262,144 tokens
Moonshot AI
Kimi K2 0905
Input262,144 tokens
Output262,144 tokens
Tue Nov 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemma 4 26B-A4B supports multimodal inputs, whereas Kimi K2 0905 does not.

Gemma 4 26B-A4B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 4 26B-A4B

Text
Images
Audio
Video

Kimi K2 0905

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 4 26B-A4B is licensed under Apache 2.0, while Kimi K2 0905 uses a proprietary license.

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

Gemma 4 26B-A4B

Apache 2.0

Open weights

Kimi K2 0905

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 4 26B-A4B was released on 2026-04-02, while Kimi K2 0905 was released on 2025-09-05.

Gemma 4 26B-A4B is 7 months newer than Kimi K2 0905.

Gemma 4 26B-A4B

Apr 2, 2026

7 months ago

6mo newer
Kimi K2 0905

Sep 5, 2025

1.2 years ago

Knowledge Cutoff

When training data ends

Gemma 4 26B-A4B has a documented knowledge cutoff of 2025-01-01, while Kimi K2 0905's cutoff date is not specified.

We can confirm Gemma 4 26B-A4B's training data extends to 2025-01-01, but cannot make a direct comparison without Kimi K2 0905's cutoff date.

Gemma 4 26B-A4B

Jan 2025

Kimi K2 0905

—

Provider Availability

Gemma 4 26B-A4B is available from DeepInfra, Novita. Kimi K2 0905 is available from Novita.

Gemma 4 26B-A4B

deepinfra logo
Deepinfra
Input Price:Input: $0.07/1MOutput Price:Output: $0.34/1M
novita logo
Novita
Input Price:Input: $0.13/1MOutput Price:Output: $0.40/1M

Kimi K2 0905

novita logo
Novita
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Gemma 4 26B-A4B and Kimi K2 0905 side-by-side, then vote on the output you prefer.

Gemma 4 26B-A4B
✓ Preferred
Kimi K2 0905
Open in Playground

FAQ

Common questions about Gemma 4 26B-A4B vs Kimi K2 0905.

Which is better, Gemma 4 26B-A4B or Kimi K2 0905?

Gemma 4 26B-A4B leads the LLM Stats Score 28.9 to 21.2. Gemma 4 26B-A4B is made by Google and Kimi K2 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 4 26B-A4B compare to Kimi K2 0905 in benchmarks?

Gemma 4 26B-A4B scores AIME 2026: 88.3%, MMMLU: 86.3%, t2-bench: 85.5%, MMLU-Pro: 82.6%, MathVision: 82.4%. Kimi K2 0905 scores HumanEval: 94.5%, MMLU: 90.2%, MATH: 89.1%, MMLU-Pro: 82.5%, GPQA: 75.8%.

Is Gemma 4 26B-A4B cheaper than Kimi K2 0905?

Gemma 4 26B-A4B is 8.6x cheaper for input tokens. Gemma 4 26B-A4B costs $0.07/M input and $0.34/M output via deepinfra. Kimi K2 0905 costs $0.60/M input and $2.50/M output via novita.

What are the context window sizes for Gemma 4 26B-A4B and Kimi K2 0905?

Gemma 4 26B-A4B supports 262K tokens and Kimi K2 0905 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 Gemma 4 26B-A4B and Kimi K2 0905?

Key differences include LLM Stats Score (28.9 vs 21.2), input pricing ($0.07 vs $0.60/M), multimodal support (yes vs no), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 4 26B-A4B and Kimi K2 0905?

Gemma 4 26B-A4B is developed by Google and Kimi K2 0905 is developed by Moonshot AI.