The AI arena is free today

Open Superagent

Hy4 preview vs Kimi K2.7 Code

Hy4 preview leads the LLM Stats Score 51.0 to 39.4.

Tencent · Moonshot AI · Updated for 2026

Which is better?

Hy4 preview leads the overall LLM Stats Score 51.0 to 39.4, ranking #14 overall.

The models split the 2 individual benchmarks reported for both models evenly.

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 agents — it leads those capability indexes
  • you want the most recent training data — it shipped Aug 2026

Choose Kimi K2.7 Code

  • you want predictable pricing at $0.68/M input and $3.40/M output

At a glance

The differences that matter most.

Hy4 preview
Tencent
Kimi K2.7 Code
Moonshot AI
Core performance indexes
LLM Stats Score
51.0
#14
39.4
#59
Reasoning
50.8
#10
34.3
#89
Coding
39.7
#14
30.7
#49
Agents
36.7
#16
27.0
#46
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
— / M
$0.68 / M
Output price
— / M
$3.40 / M
Context window
—
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Hy4 preview
Kimi K2.7 Code
Tool use
30.9#14
24.0#40
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

32 reported for Hy4 preview · 9 for Kimi K2.7 Code

2 shared

Hy4 preview outperforms in 1 benchmarks (MCP Atlas), while Kimi K2.7 Code is better at 1 benchmark (Program Bench).

Both models are evenly matched across the benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

230.0B diff

Kimi K2.7 Code has 230.0B more parameters than Hy4 preview, making it 29.9% larger.

Tencent
Hy4 preview
770.0Bparameters
Moonshot AI
Kimi K2.7 Code
1.0Tparameters
770.0B
Hy4 preview
1000.0B
Kimi K2.7 Code

Context Window

Maximum input and output token capacity

Only Kimi K2.7 Code specifies input context (262,144 tokens). Only Kimi K2.7 Code specifies output context (262,144 tokens).

Tencent
Hy4 preview
Input- tokens
Output- tokens
Moonshot AI
Kimi K2.7 Code
Input262,144 tokens
Output262,144 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Kimi K2.7 Code supports multimodal inputs, whereas Hy4 preview does not.

Kimi K2.7 Code can handle both text and other forms of data like images, making it suitable for multimodal applications.

Hy4 preview

Text
Images
Audio
Video

Kimi K2.7 Code

Text
Images
Audio
Video

License

Usage and distribution terms

Hy4 preview is licensed under Apache 2.0, while Kimi K2.7 Code uses Modified MIT License.

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

Hy4 preview

Apache 2.0

Open weights

Kimi K2.7 Code

Modified MIT License

Open weights

Release Timeline

When each model was launched

Hy4 preview was released on 2026-08-28, while Kimi K2.7 Code was released on 2026-06-12.

Hy4 preview is 3 months newer than Kimi K2.7 Code.

Hy4 preview

Aug 28, 2026

3 weeks ago

2mo newer
Kimi K2.7 Code

Jun 12, 2026

3 months 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 Hy4 preview and Kimi K2.7 Code side-by-side, then vote on the output you prefer.

Hy4 preview
✓ Preferred
Kimi K2.7 Code
Open in Playground

FAQ

Common questions about Hy4 preview vs Kimi K2.7 Code.

Which is better, Hy4 preview or Kimi K2.7 Code?

Hy4 preview leads the LLM Stats Score 51.0 to 39.4. Hy4 preview is made by Tencent and Kimi K2.7 Code 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 Hy4 preview compare to Kimi K2.7 Code 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%. Kimi K2.7 Code scores MCP-Mark: 81.1%, MCP Atlas: 76.0%, LiveBench: 71.9%, Kimi Code Bench v2: 62.0%, Program Bench: 53.6%.

What are the context window sizes for Hy4 preview and Kimi K2.7 Code?

Hy4 preview supports an unknown number of tokens and Kimi K2.7 Code supports 262K 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 Kimi K2.7 Code?

Key differences include LLM Stats Score (51.0 vs 39.4), multimodal support (no vs yes), licensing (Apache 2.0 vs Modified MIT License). See the full comparison above for benchmark-by-benchmark results.

Who makes Hy4 preview and Kimi K2.7 Code?

Hy4 preview is developed by Tencent and Kimi K2.7 Code is developed by Moonshot AI.

Related comparisons