The AI arena is free today

Open Superagent

Claude 3.7 Sonnet vs GLM-4.5-Air

Claude 3.7 Sonnet and GLM-4.5-Air are closely matched at 23.9 and 24.4 on the LLM Stats Score.

Anthropic · Zhipu AI · Updated for 2026

Which is better?

Claude 3.7 Sonnet and GLM-4.5-Air are closely matched on the overall LLM Stats Score at 23.9 and 24.4.

In the 7 individual benchmarks reported for both models, Claude 3.7 Sonnet 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 Claude 3.7 Sonnet

  • you value its reported benchmark strengths — it wins 4 of 7 exact shared results

Choose GLM-4.5-Air

  • you want the most recent training data — it shipped Jul 2025
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Claude 3.7 Sonnet
Anthropic
GLM-4.5-Air
Zhipu AI
Core performance indexes
LLM Stats Score
23.9
#168
24.4
#163
Reasoning
23.1
#164
23.8
#161
Coding
13.7
#135
11.4
#155
Agents
5.0
#147
6.0
#141
Cost, coverage & limits
Benchmark wins
4 of 7
3 of 7
Input price
$3.00 / M
— / M
Output price
$15.00 / M
— / M
Context window
200,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Claude 3.7 Sonnet
GLM-4.5-Air
Math
16.8#201
22.5#136
Tool use
17.9#70
20.2#58
Writing
18.8#25
19.6#20
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Claude 3.7 Sonnet · 14 for GLM-4.5-Air

7 shared

Claude 3.7 Sonnet outperforms in 4 benchmarks (GPQA, SWE-Bench Verified, TAU-bench Retail, Terminal-Bench), while GLM-4.5-Air is better at 3 benchmarks (AIME 2024, MATH-500, TAU-bench Airline).

Claude 3.7 Sonnet has a slight edge in benchmark performance.

Sun Sep 13 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude 3.7 Sonnet specifies input context (200,000 tokens). Only Claude 3.7 Sonnet specifies output context (128,000 tokens).

Anthropic
Claude 3.7 Sonnet
Input200,000 tokens
Output128,000 tokens
Zhipu AI
GLM-4.5-Air
Input- tokens
Output- tokens
Sun Sep 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude 3.7 Sonnet supports multimodal inputs, whereas GLM-4.5-Air does not.

Claude 3.7 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3.7 Sonnet

Text
Images
Audio
Video

GLM-4.5-Air

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3.7 Sonnet is licensed under a proprietary license, while GLM-4.5-Air uses MIT.

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

Claude 3.7 Sonnet

Proprietary

Closed source

GLM-4.5-Air

MIT

Open weights

Release Timeline

When each model was launched

Claude 3.7 Sonnet was released on 2025-02-24, while GLM-4.5-Air was released on 2025-07-28.

GLM-4.5-Air is 5 months newer than Claude 3.7 Sonnet.

Claude 3.7 Sonnet

Feb 24, 2025

1.6 years ago

GLM-4.5-Air

Jul 28, 2025

1.1 years ago

5mo 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Claude 3.7 Sonnet and GLM-4.5-Air side-by-side, then vote on the output you prefer.

Claude 3.7 Sonnet
✓ Preferred
GLM-4.5-Air
Open in Playground

FAQ

Common questions about Claude 3.7 Sonnet vs GLM-4.5-Air.

Which is better, Claude 3.7 Sonnet or GLM-4.5-Air?

Claude 3.7 Sonnet and GLM-4.5-Air are closely matched on the LLM Stats Score at 23.9 and 24.4. Claude 3.7 Sonnet is made by Anthropic and GLM-4.5-Air is made by Zhipu AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3.7 Sonnet compare to GLM-4.5-Air in benchmarks?

Claude 3.7 Sonnet scores MATH-500: 96.2%, IFEval: 93.2%, MMMLU: 86.1%, GPQA: 84.8%, TAU-bench Retail: 81.2%. 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%.

What are the context window sizes for Claude 3.7 Sonnet and GLM-4.5-Air?

Claude 3.7 Sonnet supports 200K tokens and GLM-4.5-Air 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 Claude 3.7 Sonnet and GLM-4.5-Air?

Key differences include LLM Stats Score (23.9 vs 24.4), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3.7 Sonnet and GLM-4.5-Air?

Claude 3.7 Sonnet is developed by Anthropic and GLM-4.5-Air is developed by Zhipu AI.

Related comparisons