Model Comparison

Kimi K2.5 vs Gemma 4 26B-A4B

Kimi K2.5 significantly outperforms across most benchmarks. Gemma 4 26B-A4B is 5.4x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Kimi K2.5 outperforms in 6 benchmarks (GPQA, Humanity's Last Exam, LiveCodeBench v6, MathVision, MMLU-Pro, MMMU-Pro), while Gemma 4 26B-A4B is better at 0 benchmarks.

Kimi K2.5 significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Gemma 4 26B-A4B costs less

For input processing, Kimi K2.5 ($0.60/1M tokens) is 4.6x more expensive than Gemma 4 26B-A4B ($0.13/1M tokens).

For output processing, Kimi K2.5 ($2.50/1M tokens) is 6.3x more expensive than Gemma 4 26B-A4B ($0.40/1M tokens).

In conclusion, Kimi K2.5 is more expensive than Gemma 4 26B-A4B.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
Moonshot AI
Kimi K2.5
Input tokens$0.60
Output tokens$2.50
Best providerFireworks
Google
Gemma 4 26B-A4B
Input tokens$0.13
Output tokens$0.40
Best providerNovita
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

974.8B diff

Kimi K2.5 has 974.8B more parameters than Gemma 4 26B-A4B, making it 3868.3% larger.

Moonshot AI
Kimi K2.5
1000.0Bparameters
Google
Gemma 4 26B-A4B
25.2Bparameters
1000.0B
Kimi K2.5
25.2B
Gemma 4 26B-A4B

Context Window

Maximum input and output token capacity

Gemma 4 26B-A4B accepts 262,144 input tokens compared to Kimi K2.5's 262,100 tokens. Kimi K2.5 can generate longer responses up to 262,100 tokens, while Gemma 4 26B-A4B is limited to 131,072 tokens.

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
Google
Gemma 4 26B-A4B
Input262,144 tokens
Output131,072 tokens
Thu Apr 16 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Kimi K2.5 and Gemma 4 26B-A4B support multimodal inputs.

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

Kimi K2.5

Text
Images
Audio
Video

Gemma 4 26B-A4B

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while Gemma 4 26B-A4B uses Apache 2.0.

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

Kimi K2.5

MIT

Open weights

Gemma 4 26B-A4B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while Gemma 4 26B-A4B was released on 2026-04-02.

Gemma 4 26B-A4B is 2 months newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

2 months ago

Gemma 4 26B-A4B

Apr 2, 2026

2 weeks ago

2mo newer

Knowledge Cutoff

When training data ends

Gemma 4 26B-A4B has a documented knowledge cutoff of 2025-01-01, while Kimi K2.5'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 K2.5's cutoff date.

Kimi K2.5

—

Gemma 4 26B-A4B

Jan 2025

Provider Availability

Kimi K2.5 is available from Fireworks. Gemma 4 26B-A4B is available from Novita.

Kimi K2.5

fireworks logo
Fireworks
Input Price:Input: $0.60/1MOutput Price:Output: $2.50/1M

Gemma 4 26B-A4B

novita logo
Novita
Input Price:Input: $0.13/1MOutput Price:Output: $0.40/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Moonshot AI
Higher GPQA score (87.6% vs 82.3%)
Higher Humanity's Last Exam score (50.2% vs 17.2%)
Higher LiveCodeBench v6 score (85.0% vs 77.1%)
Higher MathVision score (84.2% vs 82.4%)
Higher MMLU-Pro score (87.1% vs 82.6%)
Higher MMMU-Pro score (78.5% vs 73.8%)
Google
Larger context window (262,144 tokens)
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Moonshot AI
Kimi K2.5
Google
Gemma 4 26B-A4B

FAQ

Common questions about Kimi K2.5 vs Gemma 4 26B-A4B

Kimi K2.5 significantly outperforms across most benchmarks. Kimi K2.5 is made by Moonshot AI and Gemma 4 26B-A4B is made by Google. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. Gemma 4 26B-A4B scores AIME 2026: 88.3%, MMMLU: 86.3%, t2-bench: 85.5%, MMLU-Pro: 82.6%, MathVision: 82.4%.
Gemma 4 26B-A4B is 4.6x cheaper for input tokens. Kimi K2.5 costs $0.60/M input and $2.50/M output via fireworks. Gemma 4 26B-A4B costs $0.13/M input and $0.40/M output via novita.
Kimi K2.5 supports 262K tokens and Gemma 4 26B-A4B supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (262K vs 262K), input pricing ($0.60 vs $0.13/M), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Kimi K2.5 is developed by Moonshot AI and Gemma 4 26B-A4B is developed by Google.