The AI arena is free today

Open Superagent

Gemini 3.5 Flash-Lite vs Kimi K2-Instruct-0905

Gemini 3.5 Flash-Lite leads the LLM Stats Score 29.9 to 21.6.

Google · Moonshot AI · Updated for 2026

Which is better?

Gemini 3.5 Flash-Lite leads the overall LLM Stats Score 29.9 to 21.6, ranking #123 overall.

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

Choose Gemini 3.5 Flash-Lite

  • overall performance matters — it scores 29.9 and ranks #123 on LLM Stats
  • your work emphasizes reasoning and agents — it leads those capability indexes
  • you want the most recent training data — it shipped Jul 2026

Choose Kimi K2-Instruct-0905

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

At a glance

The differences that matter most.

Gemini 3.5 Flash-Lite
Google
Kimi K2-Instruct-0905
Moonshot AI
Core performance indexes
LLM Stats Score
29.9
#123
21.6
#185
Reasoning
25.9
#148
21.8
#175
Coding
16.0
#127
9.8
#168
Agents
15.5
#83
-4.1
#179
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.30 / M
— / M
Output price
$2.50 / M
— / M
Context window
1,048,576
—

Individual benchmarks

6 reported for Gemini 3.5 Flash-Lite · 29 for Kimi K2-Instruct-0905

No common benchmarks found

Gemini 3.5 Flash-Lite and Kimi K2-Instruct-0905don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Gemini 3.5 Flash-Lite specifies input context (1,048,576 tokens). Only Gemini 3.5 Flash-Lite specifies output context (65,536 tokens).

Google
Gemini 3.5 Flash-Lite
Input1,048,576 tokens
Output65,536 tokens
Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
Thu Sep 10 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 3.5 Flash-Lite supports multimodal inputs, whereas Kimi K2-Instruct-0905 does not.

Gemini 3.5 Flash-Lite can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemini 3.5 Flash-Lite

Text
Images
Audio
Video

Kimi K2-Instruct-0905

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 3.5 Flash-Lite is licensed under a proprietary license, while Kimi K2-Instruct-0905 uses MIT.

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

Gemini 3.5 Flash-Lite

Proprietary

Closed source

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

Gemini 3.5 Flash-Lite was released on 2026-07-21, while Kimi K2-Instruct-0905 was released on 2025-09-05.

Gemini 3.5 Flash-Lite is 11 months newer than Kimi K2-Instruct-0905.

Gemini 3.5 Flash-Lite

Jul 21, 2026

1 months ago

10mo newer
Kimi K2-Instruct-0905

Sep 5, 2025

1.0 years ago

Knowledge Cutoff

When training data ends

Gemini 3.5 Flash-Lite has a documented knowledge cutoff of 2026-03-31, while Kimi K2-Instruct-0905's cutoff date is not specified.

We can confirm Gemini 3.5 Flash-Lite's training data extends to 2026-03-31, but cannot make a direct comparison without Kimi K2-Instruct-0905's cutoff date.

Gemini 3.5 Flash-Lite

Mar 2026

Kimi K2-Instruct-0905

—

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Gemini 3.5 Flash-Lite and Kimi K2-Instruct-0905 side-by-side, then vote on the output you prefer.

Gemini 3.5 Flash-Lite
✓ Preferred
Kimi K2-Instruct-0905
Open in Playground

FAQ

Common questions about Gemini 3.5 Flash-Lite vs Kimi K2-Instruct-0905.

Which is better, Gemini 3.5 Flash-Lite or Kimi K2-Instruct-0905?

Gemini 3.5 Flash-Lite leads the LLM Stats Score 29.9 to 21.6. Gemini 3.5 Flash-Lite 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 Gemini 3.5 Flash-Lite compare to Kimi K2-Instruct-0905 in benchmarks?

Gemini 3.5 Flash-Lite scores CharXiv-R: 76.5%, OSWorld-Verified: 74.0%, SWE-Bench Pro: 54.2%, Terminal-Bench 2.1: 54.0%, MLE-Bench: 39.2%. 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 Gemini 3.5 Flash-Lite and Kimi K2-Instruct-0905?

Gemini 3.5 Flash-Lite supports 1.0M 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 Gemini 3.5 Flash-Lite and Kimi K2-Instruct-0905?

Key differences include LLM Stats Score (29.9 vs 21.6), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 3.5 Flash-Lite and Kimi K2-Instruct-0905?

Gemini 3.5 Flash-Lite is developed by Google and Kimi K2-Instruct-0905 is developed by Moonshot AI.

Related comparisons