The AI arena is free today

Open Superagent

GLM-5.2 vs Hy4 preview

Hy4 preview leads the LLM Stats Score 51.0 to 45.6.

Zhipu AI · Tencent · Updated for 2026

Which is better?

Hy4 preview leads the overall LLM Stats Score 51.0 to 45.6, ranking #14 overall.

In the 11 individual benchmarks reported for both models, Hy4 preview wins 10; 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-5.2

  • you want predictable pricing at $0.75/M input and $2.40/M output

Choose Hy4 preview

  • overall performance matters — it scores 51.0 and ranks #14 on LLM Stats
  • your work emphasizes reasoning and agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 10 of 11 exact shared results
  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

GLM-5.2
Zhipu AI
Hy4 preview
Tencent
Core performance indexes
LLM Stats Score
45.6
#28
51.0
#14
Reasoning
45.0
#31
50.8
#10
Coding
35.5
#26
39.7
#14
Agents
30.3
#34
36.7
#16
Cost, coverage & limits
Benchmark wins
1 of 11
10 of 11
Input price
$0.75 / M
— / M
Output price
$2.40 / M
— / M
Context window
1,048,576
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
GLM-5.2
Hy4 preview
Math
41.4#8
41.0#11
Tool use
22.1#47
30.9#14
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

19 reported for GLM-5.2 · 32 for Hy4 preview

11 shared

GLM-5.2 outperforms in 1 benchmarks (Program Bench), while Hy4 preview is better at 10 benchmarks (CritPT, DeepSWE, GPQA, MCP Atlas, NL2Repo, PostTrainBench, SWE-Bench Pro, SWE-Marathon, Terminal-Bench 2.1, Toolathlon).

Hy4 preview significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

17.0B diff

Hy4 preview has 17.0B more parameters than GLM-5.2, making it 2.3% larger.

Zhipu AI
GLM-5.2
753.0Bparameters
Tencent
Hy4 preview
770.0Bparameters
753.0B
GLM-5.2
770.0B
Hy4 preview

Context Window

Maximum input and output token capacity

Only GLM-5.2 specifies input context (1,048,576 tokens). Only GLM-5.2 specifies output context (1,048,576 tokens).

Zhipu AI
GLM-5.2
Input1,048,576 tokens
Output1,048,576 tokens
Tencent
Hy4 preview
Input- tokens
Output- tokens
Sun Sep 20 2026 • llm-stats.com

License

Usage and distribution terms

GLM-5.2 is licensed under MIT, while Hy4 preview uses Apache 2.0.

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

GLM-5.2

MIT

Open weights

Hy4 preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

GLM-5.2 was released on 2026-06-16, while Hy4 preview was released on 2026-08-28.

Hy4 preview is 2 months newer than GLM-5.2.

GLM-5.2

Jun 16, 2026

3 months ago

Hy4 preview

Aug 28, 2026

3 weeks ago

2mo 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 GLM-5.2 and Hy4 preview side-by-side, then vote on the output you prefer.

GLM-5.2
✓ Preferred
Hy4 preview
Open in Playground

FAQ

Common questions about GLM-5.2 vs Hy4 preview.

Which is better, GLM-5.2 or Hy4 preview?

Hy4 preview leads the LLM Stats Score 51.0 to 45.6. GLM-5.2 is made by Zhipu AI and Hy4 preview is made by Tencent. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GLM-5.2 compare to Hy4 preview in benchmarks?

GLM-5.2 scores AIME 2026: 99.2%, HMMT 2025: 94.4%, HMMT Feb 26: 92.5%, GPQA: 91.2%, IMO-AnswerBench: 91.0%. Hy4 preview scores GPQA: 92.3%, Terminal-Bench 2.1: 85.4%, WideSearch: 83.9%, MCP Atlas: 83.7%, SWE-bench Multilingual: 82.9%.

What are the context window sizes for GLM-5.2 and Hy4 preview?

GLM-5.2 supports 1.0M tokens and Hy4 preview 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-5.2 and Hy4 preview?

Key differences include LLM Stats Score (45.6 vs 51.0), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GLM-5.2 and Hy4 preview?

GLM-5.2 is developed by Zhipu AI and Hy4 preview is developed by Tencent.

Related comparisons