The AI arena is free today

Open Superagent

Kimi K2-Thinking-0905 vs MAI-Thinking-1

Kimi K2-Thinking-0905 and MAI-Thinking-1 are closely matched at 35.7 and 32.9 on the LLM Stats Score.

Moonshot AI · Microsoft · Updated for 2026

Which is better?

Kimi K2-Thinking-0905 and MAI-Thinking-1 are closely matched on the overall LLM Stats Score at 35.7 and 32.9.

In the 5 individual benchmarks reported for both models, MAI-Thinking-1 wins 3; 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-Thinking-0905

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

Choose MAI-Thinking-1

  • you value its reported benchmark strengths — it wins 3 of 5 exact shared results
  • you want the most recent training data — it shipped Jun 2026

At a glance

The differences that matter most.

Kimi K2-Thinking-0905
Moonshot AI
MAI-Thinking-1
Microsoft
Core performance indexes
LLM Stats Score
35.7
#96
32.9
#116
Reasoning
36.1
#90
33.7
#105
Coding
20.4
#107
19.0
#120
Agents
15.9
#93
12.5
#113
Cost, coverage & limits
Benchmark wins
2 of 5
3 of 5
Input price
$0.47 / M
— / M
Output price
$2.00 / M
— / M
Context window
262,144
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Kimi K2-Thinking-0905
MAI-Thinking-1
Math
37.9#28
33.7#55
Finance
19.3#87
29.2#28
Legal
18.5#81
26.7#31
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

21 reported for Kimi K2-Thinking-0905 · 23 for MAI-Thinking-1

5 shared

Kimi K2-Thinking-0905 outperforms in 2 benchmarks (AIME 2025, GPQA), while MAI-Thinking-1 is better at 3 benchmarks (LiveCodeBench v6, MMLU-Pro, SWE-Bench Verified).

MAI-Thinking-1 has a slight edge in benchmark performance.

Thu Oct 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

0.0M diff

MAI-Thinking-1 has 0.0B more parameters than Kimi K2-Thinking-0905, making it 0.0% larger.

Moonshot AI
Kimi K2-Thinking-0905
1.0Tparameters
Microsoft
MAI-Thinking-1
1.0Tparameters
1000.0B
Kimi K2-Thinking-0905
1000.0B
MAI-Thinking-1

Context Window

Maximum input and output token capacity

Only Kimi K2-Thinking-0905 specifies input context (262,144 tokens). Only Kimi K2-Thinking-0905 specifies output context (262,144 tokens).

Moonshot AI
Kimi K2-Thinking-0905
Input262,144 tokens
Output262,144 tokens
Microsoft
MAI-Thinking-1
Input- tokens
Output- tokens
Thu Oct 08 2026 • llm-stats.com

License

Usage and distribution terms

Kimi K2-Thinking-0905 is licensed under MIT, while MAI-Thinking-1 uses a proprietary license.

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

Kimi K2-Thinking-0905

MIT

Open weights

MAI-Thinking-1

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2-Thinking-0905 was released on 2025-09-05, while MAI-Thinking-1 was released on 2026-06-02.

MAI-Thinking-1 is 9 months newer than Kimi K2-Thinking-0905.

Kimi K2-Thinking-0905

Sep 5, 2025

1.1 years ago

MAI-Thinking-1

Jun 2, 2026

4 months ago

9mo 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?

Judge for yourself.

Run your own prompts against Kimi K2-Thinking-0905 and MAI-Thinking-1 side-by-side, then vote on the output you prefer.

Kimi K2-Thinking-0905
✓ Preferred
MAI-Thinking-1
Open in Playground

FAQ

Common questions about Kimi K2-Thinking-0905 vs MAI-Thinking-1.

Which is better, Kimi K2-Thinking-0905 or MAI-Thinking-1?

Kimi K2-Thinking-0905 and MAI-Thinking-1 are closely matched on the LLM Stats Score at 35.7 and 32.9. Kimi K2-Thinking-0905 is made by Moonshot AI and MAI-Thinking-1 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-Thinking-0905 compare to MAI-Thinking-1 in benchmarks?

Kimi K2-Thinking-0905 scores AIME 2025: 100.0%, HMMT 2025: 97.5%, MMLU-Redux: 94.4%, FRAMES: 87.0%, MMLU-Pro: 84.6%. MAI-Thinking-1 scores LongFact: 98.0%, AIME 2025: 97.0%, AIME 2026: 94.5%, GraphWalks: 90.0%, AIR-Bench: 88.0%.

What are the context window sizes for Kimi K2-Thinking-0905 and MAI-Thinking-1?

Kimi K2-Thinking-0905 supports 262K tokens and MAI-Thinking-1 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-Thinking-0905 and MAI-Thinking-1?

Key differences include LLM Stats Score (35.7 vs 32.9), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2-Thinking-0905 and MAI-Thinking-1?

Kimi K2-Thinking-0905 is developed by Moonshot AI and MAI-Thinking-1 is developed by Microsoft.

Related comparisons