Model Comparison

Hy3 vs Phi-3.5-MoE-instructWhich is better in 2026?

Hy3 significantly outperforms across most benchmarks.

Verdict: Hy3 vs Phi-3.5-MoE-instruct — which is better?

Hy3 (by Tencent) and Phi-3.5-MoE-instruct (by Microsoft) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Hy3 outperforms in 1 benchmarks (GPQA), while Phi-3.5-MoE-instruct is better at 0 benchmarks. Hy3 significantly outperforms across most benchmarks.

Choose Hy3 if…

  • you want the strongest raw capability — it leads on 1 of 1 shared benchmarks
  • you want the most recent training data — it shipped Jul 2026

Choose Phi-3.5-MoE-instruct if…

  • you are already invested in the Microsoft ecosystem

Performance Benchmarks

Comparative analysis across standard metrics

1 benchmarks

Hy3 outperforms in 1 benchmarks (GPQA), while Phi-3.5-MoE-instruct is better at 0 benchmarks.

Hy3 significantly outperforms across most benchmarks.

Sat Jul 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

235.0B diff

Hy3 has 235.0B more parameters than Phi-3.5-MoE-instruct, making it 391.7% larger.

Tencent
Hy3
295.0Bparameters
Microsoft
Phi-3.5-MoE-instruct
60.0Bparameters
295.0B
Hy3
60.0B
Phi-3.5-MoE-instruct

License

Usage and distribution terms

Hy3 is licensed under Apache 2.0, while Phi-3.5-MoE-instruct uses MIT.

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

Hy3

Apache 2.0

Open weights

Phi-3.5-MoE-instruct

MIT

Open weights

Release Timeline

When each model was launched

Hy3 was released on 2026-07-06, while Phi-3.5-MoE-instruct was released on 2024-08-23.

Hy3 is 23 months newer than Phi-3.5-MoE-instruct.

Hy3

Jul 6, 2026

1 weeks ago

1.9yr newer
Phi-3.5-MoE-instruct

Aug 23, 2024

1.9 years 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→

Key Takeaways

Tencent
Higher GPQA score (90.4% vs 36.8%)
Microsoft

No standout differentiators in the data we have for this pair.

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Hy3 and Phi-3.5-MoE-instruct side-by-side, then vote on the output you prefer.

Hy3
✓ Preferred
Phi-3.5-MoE-instruct
Open in Playground
AI Model Comparison Table
Feature
Tencent
Hy3
Microsoft
Phi-3.5-MoE-instruct

FAQ

Common questions about Hy3 vs Phi-3.5-MoE-instruct.

Which is better, Hy3 or Phi-3.5-MoE-instruct?

Hy3 significantly outperforms across most benchmarks. Hy3 is made by Tencent and Phi-3.5-MoE-instruct is made by Microsoft. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Hy3 compare to Phi-3.5-MoE-instruct in benchmarks?

Hy3 scores DeepSearchQA: 91.0%, GPQA: 90.4%, IMO-AnswerBench: 90.0%, BrowseComp: 84.2%, MCP Atlas: 79.1%. Phi-3.5-MoE-instruct scores ARC-C: 91.0%, OpenBookQA: 89.6%, GSM8k: 88.7%, PIQA: 88.6%, RULER: 87.1%.

What are the main differences between Hy3 and Phi-3.5-MoE-instruct?

Key differences include licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Hy3 and Phi-3.5-MoE-instruct?

Hy3 is developed by Tencent and Phi-3.5-MoE-instruct is developed by Microsoft.

Related comparisons