Gemini 3.6 Flash vs Hy3: Specs & Benchmark Comparison

Gemini 3.6 Flash is developed by Google, while Hy3 comes from Tencent. Both were released in July 2026. Hy3 has a published size of about 295 billion parameters; Google has not disclosed the parameter count of Gemini 3.6 Flash.

The two models share 2 published benchmarks. Gemini 3.6 Flash leads on 2 of them. The widest gaps are on Terminal-Bench 2.1, where Gemini 3.6 Flash scores 78.0% against 71.7%; SWE-Bench Pro, where Gemini 3.6 Flash scores 58.7% against 57.9%. Averaged across everything we track, Gemini 3.6 Flash sits at 68.0% and Hy3 at 57.1%.

Gemini 3.6 Flash is available through an API at $1.50 per million input tokens with a 1M-token context window. We do not track a hosted API for Hy3, so pricing and context cannot be compared directly.

CharacteristicGemini 3.6 FlashHy3
CompanyGoogleTencent
Release DateJuly 21, 2026July 6, 2026
Parameters295B
MultimodalYesNo
Context (input)1.0M
Context (output)66K
Input Price / 1M$1.50
Output Price / 1M$7.50
Average Score68.0%57.1%
Benchmarks
Terminal-Bench 2.178.0%71.7%
SWE-Bench Pro58.7%57.9%

Visual Benchmark Comparison

Gemini 3.6 Flash
Hy3
Terminal-Bench 2.10.8 vs 0.7
0.8
0.7
SWE-Bench Pro0.6 vs 0.6
0.6
0.6

Verdict

Gemini 3.6 Flash leads in 1 out of 2 comparison categories.

Overall Performance

Both models show comparable average scores: Gemini 3.6 Flash — 0.7, Hy3 — 0.6.

Recency

Gemini 3.6 Flash is newer: released 7/21/2026 vs 7/6/2026.

More About These Models

Related Comparisons

Frequently Asked Questions

Which is better for coding — Gemini 3.6 Flash or Hy3?
Direct comparison on the SWE-Bench benchmark is not available. We recommend reviewing other metrics on the comparison page.
Which model is cheaper — Gemini 3.6 Flash or Hy3?
API pricing data is available on the individual model pages.
Which has a larger context window — Gemini 3.6 Flash or Hy3?
Context window data is available on the individual model pages.

The Gemini 3.6 Flash and Hy3 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the Gemini 3.6 Flash or Hy3 page. See also the complete list of AI model comparisons.