The AI arena is free today

Open Superagent

GLM-4.5 vs Kimi K2-Instruct-0905

GLM-4.5 leads the LLM Stats Score 27.6 to 21.5.

Zhipu AI · Moonshot AI · Updated for 2026

Which is better?

GLM-4.5 leads the overall LLM Stats Score 27.6 to 21.5, ranking #155 overall.

In the 8 individual benchmarks reported for both models, GLM-4.5 wins 7; 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 GLM-4.5

  • overall performance matters — it scores 27.6 and ranks #155 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 7 of 8 exact shared results

Choose Kimi K2-Instruct-0905

  • you want the most recent training data — it shipped Sep 2025

At a glance

The differences that matter most.

GLM-4.5
Zhipu AI
Kimi K2-Instruct-0905
Moonshot AI
Core performance indexes
LLM Stats Score
27.6
#155
21.5
#202
Reasoning
27.1
#156
21.8
#192
Coding
15.7
#141
9.6
#184
Agents
9.8
#135
-4.2
#197
Cost, coverage & limits
Benchmark wins
7 of 8
1 of 8
Input price
$0.40 / M
— / M
Output price
$1.60 / M
— / M
Context window
131,072
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
GLM-4.5
Kimi K2-Instruct-0905
Math
26.9#104
21.5#150
Tool use
21.3#55
6.4#156
Writing
19.5#22
11.7#67
Finance
31.3#18
24.2#63
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for GLM-4.5 · 29 for Kimi K2-Instruct-0905

8 shared

GLM-4.5 outperforms in 7 benchmarks (AIME 2024, GPQA, Humanity's Last Exam, LiveCodeBench, MATH-500, MMLU-Pro, Terminal-Bench), while Kimi K2-Instruct-0905 is better at 1 benchmark (SWE-Bench Verified).

GLM-4.5 significantly outperforms across most benchmarks.

Thu Oct 08 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

645.0B diff

Kimi K2-Instruct-0905 has 645.0B more parameters than GLM-4.5, making it 181.7% larger.

Zhipu AI
GLM-4.5
355.0Bparameters
Moonshot AI
Kimi K2-Instruct-0905
1.0Tparameters
355.0B
GLM-4.5
1000.0B
Kimi K2-Instruct-0905

Context Window

Maximum input and output token capacity

Only GLM-4.5 specifies input context (131,072 tokens). Only GLM-4.5 specifies output context (131,072 tokens).

Zhipu AI
GLM-4.5
Input131,072 tokens
Output131,072 tokens
Moonshot AI
Kimi K2-Instruct-0905
Input- tokens
Output- 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.

GLM-4.5

MIT

Open weights

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

GLM-4.5 was released on 2025-07-28, while Kimi K2-Instruct-0905 was released on 2025-09-05.

Kimi K2-Instruct-0905 is 1 month newer than GLM-4.5.

GLM-4.5

Jul 28, 2025

1.2 years ago

Kimi K2-Instruct-0905

Sep 5, 2025

1.1 years ago

1mo 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 GLM-4.5 and Kimi K2-Instruct-0905 side-by-side, then vote on the output you prefer.

GLM-4.5
✓ Preferred
Kimi K2-Instruct-0905
Open in Playground

FAQ

Common questions about GLM-4.5 vs Kimi K2-Instruct-0905.

Which is better, GLM-4.5 or Kimi K2-Instruct-0905?

GLM-4.5 leads the LLM Stats Score 27.6 to 21.5. GLM-4.5 is made by Zhipu AI 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 GLM-4.5 compare to Kimi K2-Instruct-0905 in benchmarks?

GLM-4.5 scores MATH-500: 98.2%, AIME 2024: 91.0%, MMLU-Pro: 84.6%, TAU-bench Retail: 79.7%, GPQA: 79.1%. 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 GLM-4.5 and Kimi K2-Instruct-0905?

GLM-4.5 supports 131K 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 GLM-4.5 and Kimi K2-Instruct-0905?

Key differences include LLM Stats Score (27.6 vs 21.5). See the full comparison above for benchmark-by-benchmark results.

Who makes GLM-4.5 and Kimi K2-Instruct-0905?

GLM-4.5 is developed by Zhipu AI and Kimi K2-Instruct-0905 is developed by Moonshot AI.

Related comparisons