The AI arena is free today

Open Superagent

GPT-6 Luna vs Hy4 preview

GPT-6 Luna and Hy4 preview are closely matched at 44.5 and 50.4 on the LLM Stats Score.

OpenAI · Tencent · Updated for 2026

Which is better?

GPT-6 Luna and Hy4 preview are closely matched on the overall LLM Stats Score at 44.5 and 50.4.

In the 1 individual benchmarks reported for both models, GPT-6 Luna wins 1; 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 GPT-6 Luna

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you want the most recent training data — it shipped Sep 2026

Choose Hy4 preview

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
44.5
#41
50.4
#15
40.0
#58
50.2
#11
31.4
#47
38.8
#16
31.8
#30
35.9
#18
Cost, coverage & limits
Benchmark wins
1 of 1
0 of 1
Input price
$0.10 / M
— / M
Output price
$0.50 / M
— / M
Context window
1,050,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
GPT-6 Luna
Hy4 preview
22.1#47
27.7#19
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

5 reported for GPT-6 Luna · 32 for Hy4 preview

1 shared

GPT-6 Luna outperforms in 1 benchmarks (Agents' Last Exam), while Hy4 preview is better at 0 benchmarks.

GPT-6 Luna significantly outperforms across most benchmarks.

Wed Sep 23 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only GPT-6 Luna specifies input context (1,050,000 tokens). Only GPT-6 Luna specifies output context (128,000 tokens).

OpenAI
GPT-6 Luna
Input1,050,000 tokens
Output128,000 tokens
Tencent
Hy4 preview
Input- tokens
Output- tokens
Wed Sep 23 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-6 Luna supports multimodal inputs, whereas Hy4 preview does not.

GPT-6 Luna can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-6 Luna

Text
Images
Audio
Video

Hy4 preview

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-6 Luna is licensed under a proprietary license, while Hy4 preview uses Apache 2.0.

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

GPT-6 Luna

Proprietary

Closed source

Hy4 preview

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-6 Luna was released on 2026-09-22, while Hy4 preview was released on 2026-08-28.

GPT-6 Luna is 1 month newer than Hy4 preview.

GPT-6 Luna

Sep 22, 2026

0 days ago

3w newer
Hy4 preview

Aug 28, 2026

3 weeks ago

Knowledge Cutoff

When training data ends

GPT-6 Luna has a documented knowledge cutoff of 2026-05-18, while Hy4 preview's cutoff date is not specified.

We can confirm GPT-6 Luna's training data extends to 2026-05-18, but cannot make a direct comparison without Hy4 preview's cutoff date.

GPT-6 Luna

May 2026

Hy4 preview

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-6 Luna and Hy4 preview side-by-side, then vote on the output you prefer.

GPT-6 Luna
✓ Preferred
Hy4 preview
Open in Playground

FAQ

Common questions about GPT-6 Luna vs Hy4 preview.

Which is better, GPT-6 Luna or Hy4 preview?

GPT-6 Luna and Hy4 preview are closely matched on the LLM Stats Score at 44.5 and 50.4. GPT-6 Luna is made by OpenAI 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 GPT-6 Luna compare to Hy4 preview in benchmarks?

GPT-6 Luna scores DeepSWE 1.1: 66.6%, OSWorld 2.0: 52.7%, Agents' Last Exam: 50.9%, FrontierCode 1.1: 42.4%, AutomationBench v1.0.6: 20.7%. 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 GPT-6 Luna and Hy4 preview?

GPT-6 Luna supports 1.1M 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 GPT-6 Luna and Hy4 preview?

Key differences include LLM Stats Score (44.5 vs 50.4), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-6 Luna and Hy4 preview?

GPT-6 Luna is developed by OpenAI and Hy4 preview is developed by Tencent.