The AI arena is free today

Open Superagent

Hy4 preview vs Muse Glimmer-30B

Hy4 preview leads the LLM Stats Score 51.0 to 35.0.

Tencent · Meta · Updated for 2026

Which is better?

Hy4 preview leads the overall LLM Stats Score 51.0 to 35.0, ranking #14 overall.

In the 5 individual benchmarks reported for both models, Hy4 preview wins 5; 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 Hy4 preview

  • overall performance matters — it scores 51.0 and ranks #14 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 5 of 5 exact shared results
  • you want the most recent training data — it shipped Aug 2026

Choose Muse Glimmer-30B

  • you want predictable pricing at $0.30/M input and $1.20/M output

At a glance

The differences that matter most.

Hy4 preview
Tencent
Muse Glimmer-30B
Meta
Core performance indexes
LLM Stats Score
51.0
#14
35.0
#90
Reasoning
50.8
#10
34.4
#88
Coding
39.7
#14
22.3
#81
Agents
36.7
#16
16.6
#78
Cost, coverage & limits
Benchmark wins
5 of 5
0 of 5
Input price
— / M
$0.30 / M
Output price
— / M
$1.20 / M
Context window
—
131,072

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Hy4 preview
Muse Glimmer-30B
Math
41.0#11
28.4#92
Tool use
30.9#14
15.8#87
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

32 reported for Hy4 preview · 25 for Muse Glimmer-30B

5 shared

Hy4 preview outperforms in 5 benchmarks (GPQA, MCP Atlas, SkillsBench, SWE-Bench Pro, Terminal-Bench 2.1), while Muse Glimmer-30B is better at 0 benchmarks.

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

740.4B diff

Hy4 preview has 740.4B more parameters than Muse Glimmer-30B, making it 2501.4% larger.

Tencent
Hy4 preview
770.0Bparameters
Meta
Muse Glimmer-30B
29.6Bparameters
770.0B
Hy4 preview
29.6B
Muse Glimmer-30B

Context Window

Maximum input and output token capacity

Only Muse Glimmer-30B specifies input context (131,072 tokens). Only Muse Glimmer-30B specifies output context (131,072 tokens).

Tencent
Hy4 preview
Input- tokens
Output- tokens
Meta
Muse Glimmer-30B
Input131,072 tokens
Output131,072 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Muse Glimmer-30B supports multimodal inputs, whereas Hy4 preview does not.

Muse Glimmer-30B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Hy4 preview

Text
Images
Audio
Video

Muse Glimmer-30B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Hy4 preview

Apache 2.0

Open weights

Muse Glimmer-30B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Hy4 preview was released on 2026-08-28, while Muse Glimmer-30B was released on 2026-08-10.

Hy4 preview is 1 month newer than Muse Glimmer-30B.

Hy4 preview

Aug 28, 2026

3 weeks ago

2w newer
Muse Glimmer-30B

Aug 10, 2026

1 months ago

Knowledge Cutoff

When training data ends

Muse Glimmer-30B has a documented knowledge cutoff of 2026-01-04, while Hy4 preview's cutoff date is not specified.

We can confirm Muse Glimmer-30B's training data extends to 2026-01-04, but cannot make a direct comparison without Hy4 preview's cutoff date.

Hy4 preview

—

Muse Glimmer-30B

Jan 2026

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Hy4 preview and Muse Glimmer-30B side-by-side, then vote on the output you prefer.

Hy4 preview
✓ Preferred
Muse Glimmer-30B
Open in Playground

FAQ

Common questions about Hy4 preview vs Muse Glimmer-30B.

Which is better, Hy4 preview or Muse Glimmer-30B?

Hy4 preview leads the LLM Stats Score 51.0 to 35.0. Hy4 preview is made by Tencent and Muse Glimmer-30B is made by Meta. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Hy4 preview compare to Muse Glimmer-30B in benchmarks?

Hy4 preview scores GPQA: 92.3%, Terminal-Bench 2.1: 85.4%, WideSearch: 83.9%, MCP Atlas: 83.7%, SWE-bench Multilingual: 82.9%. Muse Glimmer-30B scores AIME 2026: 94.7%, Siren AgentDojo Utility: 94.2%, GPQA: 83.5%, AA-LCR: 80.0%, CharXiv-R: 78.8%.

What are the context window sizes for Hy4 preview and Muse Glimmer-30B?

Hy4 preview supports an unknown number of tokens and Muse Glimmer-30B supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Hy4 preview and Muse Glimmer-30B?

Key differences include LLM Stats Score (51.0 vs 35.0), multimodal support (no vs yes). See the full comparison above for benchmark-by-benchmark results.

Who makes Hy4 preview and Muse Glimmer-30B?

Hy4 preview is developed by Tencent and Muse Glimmer-30B is developed by Meta.

Related comparisons