The AI arena is free today

Open Superagent

Kimi K2-Instruct-0905 vs MiniMax M1 80K

Kimi K2-Instruct-0905 and MiniMax M1 80K are closely matched at 21.5 and 21.4 on the LLM Stats Score.

Moonshot AI · MiniMax · Updated for 2026

Which is better?

Kimi K2-Instruct-0905 and MiniMax M1 80K are closely matched on the overall LLM Stats Score at 21.5 and 21.4.

In the 11 individual benchmarks reported for both models, Kimi K2-Instruct-0905 wins 6; 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-Instruct-0905

  • you value its reported benchmark strengths — it wins 6 of 11 exact shared results
  • you want the most recent training data — it shipped Sep 2025

Choose MiniMax M1 80K

  • you want predictable pricing at $0.55/M input and $2.20/M output

At a glance

The differences that matter most.

Kimi K2-Instruct-0905
Moonshot AI
MiniMax M1 80K
MiniMax
Core performance indexes
LLM Stats Score
21.5
#202
21.4
#204
Reasoning
21.8
#192
21.6
#193
Coding
9.6
#184
9.4
#185
Cost, coverage & limits
Benchmark wins
6 of 11
5 of 11
Input price
— / M
$0.55 / M
Output price
— / M
$2.20 / M
Context window
—
1,000,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Kimi K2-Instruct-0905
MiniMax M1 80K
Math
21.5#150
19.6#171
Tool use
6.4#156
14.6#105
Writing
11.7#67
14.6#50
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

29 reported for Kimi K2-Instruct-0905 · 16 for MiniMax M1 80K

11 shared

Kimi K2-Instruct-0905 outperforms in 6 benchmarks (GPQA, MATH-500, Multi-Challenge, SimpleQA, SWE-Bench Verified, ZebraLogic), while MiniMax M1 80K is better at 4 benchmarks (AIME 2024, AIME 2025, Humanity's Last Exam, LiveCodeBench).

Kimi K2-Instruct-0905 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

544.0B diff

Kimi K2-Instruct-0905 has 544.0B more parameters than MiniMax M1 80K, making it 119.3% larger.

Moonshot AI
Kimi K2-Instruct-0905
1.0Tparameters
MiniMax
MiniMax M1 80K
456.0Bparameters
1000.0B
Kimi K2-Instruct-0905
456.0B
MiniMax M1 80K

Context Window

Maximum input and output token capacity

Only MiniMax M1 80K specifies input context (1,000,000 tokens). Only MiniMax M1 80K specifies output context (40,000 tokens).

Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- tokens
MiniMax
MiniMax M1 80K
Input1,000,000 tokens
Output40,000 tokens
Thu Oct 08 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under MIT.

Both models share the same licensing terms, providing consistent usage rights.

Kimi K2-Instruct-0905

MIT

Open weights

MiniMax M1 80K

MIT

Open weights

Release Timeline

When each model was launched

Kimi K2-Instruct-0905 was released on 2025-09-05, while MiniMax M1 80K was released on 2025-06-16.

Kimi K2-Instruct-0905 is 3 months newer than MiniMax M1 80K.

Kimi K2-Instruct-0905

Sep 5, 2025

1.1 years ago

2mo newer
MiniMax M1 80K

Jun 16, 2025

1.3 years 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 Kimi K2-Instruct-0905 and MiniMax M1 80K side-by-side, then vote on the output you prefer.

Kimi K2-Instruct-0905
✓ Preferred
MiniMax M1 80K
Open in Playground

FAQ

Common questions about Kimi K2-Instruct-0905 vs MiniMax M1 80K.

Which is better, Kimi K2-Instruct-0905 or MiniMax M1 80K?

Kimi K2-Instruct-0905 and MiniMax M1 80K are closely matched on the LLM Stats Score at 21.5 and 21.4. Kimi K2-Instruct-0905 is made by Moonshot AI and MiniMax M1 80K 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 M1 80K 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 M1 80K scores MATH-500: 96.8%, ZebraLogic: 86.8%, AIME 2024: 86.0%, MMLU-Pro: 81.1%, AIME 2025: 76.9%.

What are the context window sizes for Kimi K2-Instruct-0905 and MiniMax M1 80K?

Kimi K2-Instruct-0905 supports an unknown number of tokens and MiniMax M1 80K 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 M1 80K?

Key differences include LLM Stats Score (21.5 vs 21.4). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K2-Instruct-0905 and MiniMax M1 80K?

Kimi K2-Instruct-0905 is developed by Moonshot AI and MiniMax M1 80K is developed by MiniMax.

Related comparisons