The AI arena is free today

Open Superagent

Kimi K2.5 vs MAI-Code-1-Flash

Kimi K2.5 leads the LLM Stats Score 39.1 to 29.3.

Moonshot AI · Microsoft · Updated for 2026

Which is better?

Kimi K2.5 leads the overall LLM Stats Score 39.1 to 29.3, ranking #58 overall.

In the 6 individual benchmarks reported for both models, Kimi K2.5 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 Kimi K2.5

  • overall performance matters — it scores 39.1 and ranks #58 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 6 exact shared results
  • you need open weights you can self-host or fine-tune

Choose MAI-Code-1-Flash

  • you want the most recent training data — it shipped Jun 2026

At a glance

The differences that matter most.

Kimi K2.5
Moonshot AI
MAI-Code-1-Flash
Microsoft
Core performance indexes
LLM Stats Score
39.1
#58
29.3
#122
Reasoning
39.1
#55
29.0
#115
Coding
25.2
#65
19.8
#96
Agents
17.8
#65
10.9
#101
Cost, coverage & limits
Benchmark wins
4 of 6
2 of 6
Input price
$0.60 / M
— / M
Output price
$3.00 / M
— / M
Context window
262,100
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Kimi K2.5
MAI-Code-1-Flash
Math
36.5#36
21.6#139
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

40 reported for Kimi K2.5 · 15 for MAI-Code-1-Flash

6 shared

Kimi K2.5 outperforms in 4 benchmarks (GPQA, Humanity's Last Exam, SWE-bench Multilingual, SWE-Bench Verified), while MAI-Code-1-Flash is better at 2 benchmarks (SWE-Bench Pro, Terminal-Bench 2.0).

Kimi K2.5 shows notably better performance in the majority of benchmarks.

Fri Sep 04 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).

Moonshot AI
Kimi K2.5
Input262,100 tokens
Output262,100 tokens
Microsoft
MAI-Code-1-Flash
Input- tokens
Output- tokens
Fri Sep 04 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Kimi K2.5 supports multimodal inputs, whereas MAI-Code-1-Flash does not.

Kimi K2.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2.5

Text
Images
Audio
Video

MAI-Code-1-Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2.5 is licensed under MIT, while MAI-Code-1-Flash uses a proprietary license.

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

Kimi K2.5

MIT

Open weights

MAI-Code-1-Flash

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2.5 was released on 2026-01-27, while MAI-Code-1-Flash was released on 2026-06-02.

MAI-Code-1-Flash is 4 months newer than Kimi K2.5.

Kimi K2.5

Jan 27, 2026

7 months ago

MAI-Code-1-Flash

Jun 2, 2026

3 months ago

4mo newer

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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Kimi K2.5 and MAI-Code-1-Flash side-by-side, then vote on the output you prefer.

Kimi K2.5
✓ Preferred
MAI-Code-1-Flash
Open in Playground

FAQ

Common questions about Kimi K2.5 vs MAI-Code-1-Flash.

Which is better, Kimi K2.5 or MAI-Code-1-Flash?

Kimi K2.5 leads the LLM Stats Score 39.1 to 29.3. Kimi K2.5 is made by Moonshot AI and MAI-Code-1-Flash is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi K2.5 compare to MAI-Code-1-Flash in benchmarks?

Kimi K2.5 scores AIME 2025: 96.1%, HMMT 2025: 95.4%, InfoVQAtest: 92.6%, OCRBench: 92.3%, MathVista-Mini: 90.1%. MAI-Code-1-Flash scores AIME 2026: 92.5%, GPQA: 84.6%, IFBench: 75.0%, Tau2 Telecom: 71.7%, SWE-Bench Verified: 71.6%.

What are the context window sizes for Kimi K2.5 and MAI-Code-1-Flash?

Kimi K2.5 supports 262K tokens and MAI-Code-1-Flash 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 Kimi K2.5 and MAI-Code-1-Flash?

Key differences include LLM Stats Score (39.1 vs 29.3), multimodal support (yes vs no), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2.5 and MAI-Code-1-Flash?

Kimi K2.5 is developed by Moonshot AI and MAI-Code-1-Flash is developed by Microsoft.

Related comparisons