The AI arena is free today

Open Superagent

Hy3 vs Sakana Namazu

Hy3 and Sakana Namazu are closely matched at 43.2 and 42.1 on the LLM Stats Score. Hy3 is 6.8x cheaper per token.

Tencent · Sakana AI · Updated for 2026

Which is better?

Hy3 and Sakana Namazu are closely matched on the overall LLM Stats Score at 43.2 and 42.1.

On price, Hy3 is roughly 6.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Hy3 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Hy3

  • cost matters — it's about 6.8x cheaper per token
  • you process long inputs — it offers a 262,144 token context window
  • you need open weights you can self-host or fine-tune

Choose Sakana Namazu

  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

Core performance indexes
43.2
#41
42.1
#48
43.1
#42
41.9
#47
Cost, coverage & limits
Benchmark wins
Input price
$0.14 / M
$0.95 / M
Output price
$0.58 / M
$4.00 / M
Context window
262,144
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Hy3
Sakana Namazu
36.9#33
38.4#26
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

31 reported for Hy3 · 3 for Sakana Namazu

No common benchmarks found

Hy3 and Sakana Namazudon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Hy3 costs less

For input processing, Hy3 ($0.14/1M tokens) is 6.8x cheaper than Sakana Namazu ($0.95/1M tokens).

For output processing, Hy3 ($0.58/1M tokens) is 6.9x cheaper than Sakana Namazu ($4.00/1M tokens).

In conclusion, Sakana Namazu is more expensive than Hy3.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Thu Sep 17 2026 • llm-stats.com
Tencent
Hy3
Input tokens$0.14
Output tokens$0.58
Best providerDeepinfra
Sakana AI
Sakana Namazu
Input tokens$0.95
Output tokens$4.00
Best providerUnknown Organization
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Hy3 accepts 262,144 input tokens compared to Sakana Namazu's 256,000 tokens. Hy3 can generate longer responses up to 262,144 tokens, while Sakana Namazu is limited to 256,000 tokens.

Tencent
Hy3
Input262,144 tokens
Output262,144 tokens
Sakana AI
Sakana Namazu
Input256,000 tokens
Output256,000 tokens
Thu Sep 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Sakana Namazu supports multimodal inputs, whereas Hy3 does not.

Sakana Namazu can handle both text and other forms of data like images, making it suitable for multimodal applications.

Hy3

Text
Images
Audio
Video

Sakana Namazu

Text
Images
Audio
Video

License

Usage and distribution terms

Hy3 is licensed under Apache 2.0, while Sakana Namazu uses a proprietary license.

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

Hy3

Apache 2.0

Open weights

Sakana Namazu

Proprietary

Closed source

Release Timeline

When each model was launched

Hy3 was released on 2026-07-06, while Sakana Namazu was released on 2026-08-03.

Sakana Namazu is 1 month newer than Hy3.

Hy3

Jul 6, 2026

2 months ago

Sakana Namazu

Aug 3, 2026

1 months ago

4w 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

Provider Availability

Hy3 is available from DeepInfra. Sakana Namazu is available from Sakana AI.

Hy3

deepinfra logo
Deepinfra
Input Price:Input: $0.14/1MOutput Price:Output: $0.58/1M

Sakana Namazu

sakana logo
Unknown Organization
Input Price:Input: $0.95/1MOutput Price:Output: $4.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Hy3 and Sakana Namazu side-by-side, then vote on the output you prefer.

Hy3
✓ Preferred
Sakana Namazu
Open in Playground

FAQ

Common questions about Hy3 vs Sakana Namazu.

Which is better, Hy3 or Sakana Namazu?

Hy3 and Sakana Namazu are closely matched on the LLM Stats Score at 43.2 and 42.1. Hy3 is made by Tencent and Sakana Namazu is made by Sakana AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Hy3 compare to Sakana Namazu in benchmarks?

Hy3 scores DeepSearchQA: 91.0%, GPQA: 90.4%, IMO-AnswerBench: 90.0%, BrowseComp: 84.2%, MCP Atlas: 79.1%. Sakana Namazu scores AIME 2026: 96.7%, LiveCodeBench v6: 90.3%, MMLU-Pro: 90.3%.

Is Hy3 cheaper than Sakana Namazu?

Hy3 is 6.8x cheaper for input tokens. Hy3 costs $0.14/M input and $0.58/M output via deepinfra. Sakana Namazu costs $0.95/M input and $4.00/M output via sakana.

What are the context window sizes for Hy3 and Sakana Namazu?

Hy3 supports 262K tokens and Sakana Namazu supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Hy3 and Sakana Namazu?

Key differences include LLM Stats Score (43.2 vs 42.1), context window (262K vs 256K), input pricing ($0.14 vs $0.95/M), multimodal support (no vs yes), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Hy3 and Sakana Namazu?

Hy3 is developed by Tencent and Sakana Namazu is developed by Sakana AI.