The AI arena is free today

Open Superagent

Gemini 4 Argon vs Kimi K2.5

Gemini 4 Argon leads the LLM Stats Score 55.1 to 38.6.

Google · Moonshot AI · Updated for 2026

Which is better?

Gemini 4 Argon leads the overall LLM Stats Score 55.1 to 38.6, ranking #4 overall.

In the 1 individual benchmarks reported for both models, Gemini 4 Argon wins 1; 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 Gemini 4 Argon

  • overall performance matters — it scores 55.1 and ranks #4 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Sep 2026

Choose Kimi K2.5

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Gemini 4 Argon
Google
Kimi K2.5
Moonshot AI
Core performance indexes
LLM Stats Score
55.1
#4
38.6
#73
Reasoning
52.4
#7
38.5
#73
Coding
44.1
#4
24.5
#83
Agents
40.5
#4
17.7
#86
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
— / M
$0.60 / M
Output price
— / M
$3.00 / M
Context window
—
262,100

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Gemini 4 Argon
Kimi K2.5
Vision
36.8#8
27.3#42
Long context
30.6#3
25.6#13
Multimodal
36.9#8
29.1#34
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

19 reported for Gemini 4 Argon · 40 for Kimi K2.5

1 shared

Gemini 4 Argon outperforms in 1 benchmarks (LVBench), while Kimi K2.5 is better at 0 benchmarks.

Gemini 4 Argon significantly outperforms across most benchmarks.

Thu Oct 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Kimi K2.5 specifies input context (262,100 tokens). Only Kimi K2.5 specifies output context (262,100 tokens).

Google
Gemini 4 Argon
Input- tokens
Output- tokens
Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
Thu Oct 08 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Gemini 4 Argon and Kimi K2.5 support multimodal inputs.

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

Gemini 4 Argon

Text
Images
Audio
Video

Kimi K2.5

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 4 Argon is licensed under a proprietary license, while Kimi K2.5 uses MIT.

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

Gemini 4 Argon

Proprietary

Closed source

Kimi K2.5

MIT

Open weights

Release Timeline

When each model was launched

Gemini 4 Argon was released on 2026-09-30, while Kimi K2.5 was released on 2026-01-27.

Gemini 4 Argon is 8 months newer than Kimi K2.5.

Gemini 4 Argon

Sep 30, 2026

1 weeks ago

8mo newer
Kimi K2.5

Jan 27, 2026

8 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Gemini 4 Argon and Kimi K2.5 side-by-side, then vote on the output you prefer.

Gemini 4 Argon
✓ Preferred
Kimi K2.5
Open in Playground

FAQ

Common questions about Gemini 4 Argon vs Kimi K2.5.

Which is better, Gemini 4 Argon or Kimi K2.5?

Gemini 4 Argon leads the LLM Stats Score 55.1 to 38.6. Gemini 4 Argon is made by Google and Kimi K2.5 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 Gemini 4 Argon compare to Kimi K2.5 in benchmarks?

Gemini 4 Argon scores Graphwalks BFS <128k: 99.7%, Vibe Code Bench: 91.9%, LVBench: 91.7%, LABBench2: 88.8%, Graphwalks BFS >128k: 84.2%. Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%.

What are the context window sizes for Gemini 4 Argon and Kimi K2.5?

Gemini 4 Argon supports an unknown number of tokens and Kimi K2.5 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 Gemini 4 Argon and Kimi K2.5?

Key differences include LLM Stats Score (55.1 vs 38.6), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 4 Argon and Kimi K2.5?

Gemini 4 Argon is developed by Google and Kimi K2.5 is developed by Moonshot AI.

Related comparisons