Hy3

tencent/hy3

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Compare

Context window: 256K
Input: Text
Output: Text
Released: 2026-07-06

Max output: 64K
Model parameters: 299B
Active parameters: 21B
Weights: Open
License: apache-2.0
Capabilities: Open weight, Reasoning, Temperature, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

Overall capability

49.3/100

Coding: 45.4
Reasoning: 52.1
Professional work: 48.5
Knowledge & language: 60.7


Arena Agent Overall	Professional work	LMArena	2026-11-08
SciCodeHy3	Coding	Artificial Analysis	2026-11-05
GDPval-AA	Professional work	Artificial Analysis	2026-11-05
AutomationBench-AAHy3	Professional work	Artificial Analysis	2026-11-05
Terminal-Bench 4.0 (AA rerun)Hy3	Coding	Artificial Analysis	2026-11-05
Humanity’s Last ExamHy3	Reasoning	Artificial Analysis	2026-11-05
AA-LCRHy3	Knowledge & language	Artificial Analysis	2026-11-05
AA-Briefcase	Professional work	Artificial Analysis	2026-11-05

Providers

No providers found

ModelRegistry · Catalog updated 2026-11-10