The AI arena is free today

Open Superagent

GLM-4.5-Air vs Kimi K2 Instruct

GLM-4.5-Air and Kimi K2 Instruct are closely matched at 24.6 and 22.0 on the LLM Stats Score.

Zhipu AI · Moonshot AI · Updated for 2026

Which is better?

GLM-4.5-Air and Kimi K2 Instruct are closely matched on the overall LLM Stats Score at 24.6 and 22.0.

In the 6 individual benchmarks reported for both models, GLM-4.5-Air 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 GLM-4.5-Air

  • you value its reported benchmark strengths — it wins 4 of 6 exact shared results
  • you want the most recent training data — it shipped Jul 2025

Choose Kimi K2 Instruct

  • you want predictable pricing at $0.50/M input and $0.50/M output

At a glance

The differences that matter most.

GLM-4.5-Air
Zhipu AI
Kimi K2 Instruct
Moonshot AI
Core performance indexes
LLM Stats Score
24.6
#153
22.0
#171
Reasoning
24.0
#151
22.1
#163
Coding
11.6
#148
12.6
#138
Agents
6.1
#134
-0.9
#164
Cost, coverage & limits
Benchmark wins
4 of 6
2 of 6
Input price
— / M
$0.50 / M
Output price
— / M
$0.50 / M
Context window
—
200,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
GLM-4.5-Air
Kimi K2 Instruct
Math
22.7#128
22.5#131
Tool use
20.3#55
7.4#136
Writing
19.3#20
11.8#61
Finance
26.7#41
24.4#58
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for GLM-4.5-Air · 38 for Kimi K2 Instruct

6 shared

GLM-4.5-Air outperforms in 4 benchmarks (AIME 2024, Humanity's Last Exam, MATH-500, MMLU-Pro), while Kimi K2 Instruct is better at 1 benchmark (GPQA).

GLM-4.5-Air 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

Model Size

Parameter count comparison

894.0B diff

Kimi K2 Instruct has 894.0B more parameters than GLM-4.5-Air, making it 843.4% larger.

Zhipu AI
GLM-4.5-Air
106.0Bparameters
Moonshot AI
Kimi K2 Instruct
1.0Tparameters
106.0B
GLM-4.5-Air
1000.0B
Kimi K2 Instruct

Context Window

Maximum input and output token capacity

Only Kimi K2 Instruct specifies input context (200,000 tokens). Only Kimi K2 Instruct specifies output context (200,000 tokens).

Zhipu AI
GLM-4.5-Air
Input- tokens
Output- tokens
Moonshot AI
Kimi K2 Instruct
Input200,000 tokens
Output200,000 tokens
Fri Sep 04 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-Air

MIT

Open weights

Kimi K2 Instruct

MIT

Open weights

Release Timeline

When each model was launched

GLM-4.5-Air was released on 2025-07-28, while Kimi K2 Instruct was released on 2025-07-11.

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

GLM-4.5-Air

Jul 28, 2025

1.1 years ago

2w newer
Kimi K2 Instruct

Jul 11, 2025

1.1 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against GLM-4.5-Air and Kimi K2 Instruct side-by-side, then vote on the output you prefer.

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

FAQ

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

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

GLM-4.5-Air and Kimi K2 Instruct are closely matched on the LLM Stats Score at 24.6 and 22.0. GLM-4.5-Air is made by Zhipu AI and Kimi K2 Instruct 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-Air compare to Kimi K2 Instruct in benchmarks?

GLM-4.5-Air scores MATH-500: 98.1%, AIME 2024: 89.4%, MMLU-Pro: 81.4%, TAU-bench Retail: 77.9%, BFCL-v3: 76.4%. Kimi K2 Instruct scores MATH-500: 97.4%, GSM8k: 97.3%, CBNSL: 95.6%, HumanEval: 93.3%, MMLU-Redux: 92.7%.

What are the context window sizes for GLM-4.5-Air and Kimi K2 Instruct?

GLM-4.5-Air supports an unknown number of tokens and Kimi K2 Instruct supports 200K 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-Air and Kimi K2 Instruct?

Key differences include LLM Stats Score (24.6 vs 22.0). See the full comparison above for benchmark-by-benchmark results.

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

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

Related comparisons