Model Comparison

MAI-Thinking-1 vs Hy3Which is better in 2026?

Hy3 significantly outperforms across most benchmarks.

Verdict: MAI-Thinking-1 vs Hy3 — which is better?

MAI-Thinking-1 (by Microsoft) and Hy3 (by Tencent) 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.

MAI-Thinking-1 outperforms in 0 benchmarks, while Hy3 is better at 3 benchmarks (GPQA, SWE-Bench Pro, SWE-Bench Verified). Hy3 significantly outperforms across most benchmarks.

Choose MAI-Thinking-1 if…

  • you are already invested in the Microsoft ecosystem

Choose Hy3 if…

  • you want the strongest raw capability — it leads on 3 of 3 shared benchmarks
  • you want the most recent training data — it shipped Jul 2026
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

MAI-Thinking-1 outperforms in 0 benchmarks, while Hy3 is better at 3 benchmarks (GPQA, SWE-Bench Pro, SWE-Bench Verified).

Hy3 significantly outperforms across most benchmarks.

Fri Jul 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

705.0B diff

MAI-Thinking-1 has 705.0B more parameters than Hy3, making it 239.0% larger.

Microsoft
MAI-Thinking-1
1.0Tparameters
Tencent
Hy3
295.0Bparameters
1000.0B
MAI-Thinking-1
295.0B
Hy3

License

Usage and distribution terms

MAI-Thinking-1 is licensed under a proprietary license, while Hy3 uses Apache 2.0.

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

MAI-Thinking-1

Proprietary

Closed source

Hy3

Apache 2.0

Open weights

Release Timeline

When each model was launched

MAI-Thinking-1 was released on 2026-06-02, while Hy3 was released on 2026-07-06.

Hy3 is 1 month newer than MAI-Thinking-1.

MAI-Thinking-1

Jun 2, 2026

1 months ago

Hy3

Jul 6, 2026

1 weeks ago

1mo 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Microsoft

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

Tencent
Has open weights
Higher GPQA score (90.4% vs 84.2%)
Higher SWE-Bench Pro score (57.9% vs 52.8%)
Higher SWE-Bench Verified score (78.0% vs 73.5%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against MAI-Thinking-1 and Hy3 side-by-side, then vote on the output you prefer.

MAI-Thinking-1
✓ Preferred
Hy3
Open in Playground
AI Model Comparison Table
Feature
Microsoft
MAI-Thinking-1
Tencent
Hy3

FAQ

Common questions about MAI-Thinking-1 vs Hy3.

Which is better, MAI-Thinking-1 or Hy3?

Hy3 significantly outperforms across most benchmarks. MAI-Thinking-1 is made by Microsoft and Hy3 is made by Tencent. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does MAI-Thinking-1 compare to Hy3 in benchmarks?

MAI-Thinking-1 scores LongFact: 98.0%, AIME 2025: 97.0%, AIME 2026: 94.5%, GraphWalks: 90.0%, AIR-Bench: 88.0%. Hy3 scores DeepSearchQA: 91.0%, GPQA: 90.4%, IMO-AnswerBench: 90.0%, BrowseComp: 84.2%, MCP Atlas: 79.1%.

What are the main differences between MAI-Thinking-1 and Hy3?

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

Who makes MAI-Thinking-1 and Hy3?

MAI-Thinking-1 is developed by Microsoft and Hy3 is developed by Tencent.

Related comparisons