The AI arena is free today

Open Superagent

Kimi K2-Instruct-0905 vs MiniMax M3.1 Flash

MiniMax M3.1 Flash leads the LLM Stats Score 48.5 to 21.3.

Moonshot AI · MiniMax · Updated for 2026

Which is better?

MiniMax M3.1 Flash leads the overall LLM Stats Score 48.5 to 21.3, ranking #29 overall.

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

Choose Kimi K2-Instruct-0905

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

Choose MiniMax M3.1 Flash

  • overall performance matters — it scores 48.5 and ranks #29 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Kimi K2-Instruct-0905
Moonshot AI
MiniMax M3.1 Flash
MiniMax
Core performance indexes
LLM Stats Score
21.3
#210
48.5
#29
Reasoning
21.6
#199
45.8
#34
Coding
9.5
#191
37.8
#23
Agents
-4.2
#205
35.6
#23
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.15 / M
Output price
— / M
$0.60 / M
Context window
—
1,000,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Kimi K2-Instruct-0905
MiniMax M3.1 Flash
Tool use
6.3#162
26.8#30
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

29 reported for Kimi K2-Instruct-0905 · 14 for MiniMax M3.1 Flash

No common benchmarks found

Kimi K2-Instruct-0905 and MiniMax M3.1 Flashdon'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 MiniMax M3.1 Flash specifies input context (1,000,000 tokens). Only MiniMax M3.1 Flash specifies output context (524,288 tokens).

Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
MiniMax
MiniMax M3.1 Flash
Input1,000,000 tokens
Output524,288 tokens
Mon Oct 19 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

MiniMax M3.1 Flash supports multimodal inputs, whereas Kimi K2-Instruct-0905 does not.

MiniMax M3.1 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Kimi K2-Instruct-0905

Text
Images
Audio
Video

MiniMax M3.1 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Kimi K2-Instruct-0905 is licensed under MIT, while MiniMax M3.1 Flash uses a proprietary license.

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

Kimi K2-Instruct-0905

MIT

Open weights

MiniMax M3.1 Flash

Proprietary

Closed source

Release Timeline

When each model was launched

Kimi K2-Instruct-0905 was released on 2025-09-05, while MiniMax M3.1 Flash was released on 2026-10-19.

MiniMax M3.1 Flash is 14 months newer than Kimi K2-Instruct-0905.

Kimi K2-Instruct-0905

Sep 5, 2025

1.1 years ago

MiniMax M3.1 Flash

Oct 19, 2026

0 days ago

1.1yr 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-Instruct-0905 and MiniMax M3.1 Flash side-by-side, then vote on the output you prefer.

Kimi K2-Instruct-0905
✓ Preferred
MiniMax M3.1 Flash
Open in Playground

FAQ

Common questions about Kimi K2-Instruct-0905 vs MiniMax M3.1 Flash.

Which is better, Kimi K2-Instruct-0905 or MiniMax M3.1 Flash?

MiniMax M3.1 Flash leads the LLM Stats Score 48.5 to 21.3. Kimi K2-Instruct-0905 is made by Moonshot AI and MiniMax M3.1 Flash is made by MiniMax. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Kimi K2-Instruct-0905 compare to MiniMax M3.1 Flash in benchmarks?

Kimi K2-Instruct-0905 scores MATH-500: 97.4%, MMLU-Redux: 92.7%, IFEval: 89.8%, AutoLogi: 89.5%, MMLU: 89.5%. MiniMax M3.1 Flash scores BabyVision: 91.0%, CharXiv-R: 82.5%, CyberGym: 82.2%, BankerToolBench: 76.2%, DeepSWE 1.1: 73.7%.

What are the context window sizes for Kimi K2-Instruct-0905 and MiniMax M3.1 Flash?

Kimi K2-Instruct-0905 supports an unknown number of tokens and MiniMax M3.1 Flash supports 1.0M 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-Instruct-0905 and MiniMax M3.1 Flash?

Key differences include LLM Stats Score (21.3 vs 48.5), multimodal support (no vs yes), licensing (MIT vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2-Instruct-0905 and MiniMax M3.1 Flash?

Kimi K2-Instruct-0905 is developed by Moonshot AI and MiniMax M3.1 Flash is developed by MiniMax.

Related comparisons