ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Tencent 腾讯混元
Open-Weight Tencent 腾讯混元 · hy3 · Text

Hy3 Official Specifications, Pricing & Benchmarks

Hy3 (hy3) by Tencent 腾讯混元, released 2026-07-06, featuring 262,144 context window, 128,000 max output tokens, and Text input.

📋 Hy3 Official API & System Card Specifications

Verified against official Tencent 腾讯混元 developer documentation & pricing

API Model ID: hy3

1. Identity & Capabilities

API Spec
API Model ID
hy3
Release Date
2026-07-06
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
262,000 tokens (262K)
Max Output Tokens
128,000 tokens
Input Modalities
Text
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.132
Cached Input / 1M
$ 0.033 -75%
Output / 1M Tokens
$ 0.528

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=0.7 top_p=0.95 max_tokens=65,536

📊 Hy3 Full Benchmark Scorecard

29 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 11 items

MCP Atlas #12/39 79.1%

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

SWE-Bench Verified #18/59 78%

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

SWE-bench Multilingual #15/33 75.8%

A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.

Terminal-Bench 2.1 #23/37 71.7%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

Claw-Eval #6/13 68.5%

Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.

SWE-Bench Pro #25/52 57.9%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

SkillsBench #4/11 55.3%

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

WildClawBench #3/5 53.6%

WildClawBench is an agentic coding benchmark from InternLM/Claw-Eval that reports overall model performance on real-world tool-using development tasks.

NL2Repo #14/23 45.6%

NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.

DeepSWE #11/12 28%

DeepSWE is a software engineering agent benchmark evaluated with the mini-swe-agent harness, where each task is solved in an isolated container with no internet access. It measures an agent's ability to autonomously resolve real-world coding issues end to end.

CL-bench #1/3 23.8%

CL-bench is an open-source benchmark with its own data and rubrics for evaluating models on coding and agentic tasks, scored using a setup fully aligned with the official procedure.

📐 Math 8 items

IMO-AnswerBench #3/17 90%

IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.

FrontierScience Olympiad #2/3 74.8%

FrontierScience Olympiad is a benchmark of olympiad-level scientific reasoning problems, testing expert understanding and multi-step reasoning across advanced natural-science domains.

USAMO 2026 #3/3 30.2

USAMO 2026 evaluates models on the six problems from the 2026 United States of America Mathematical Olympiad, requiring rigorous proof-based reasoning.

Humanity's Last Exam (with tools, text-only) #5/10 53.2%

Text-only Humanity's Last Exam variant evaluated with tool use enabled.

ArXivMath #5/6 52.2%

ArXivMath is a final-answer benchmark of research-level mathematics maintained by MathArena. Problems are extracted monthly from recent arXiv paper abstracts, then filtered through automated and manual checks to ensure they are self-contained, non-trivial, and verifiable.

Humanity's Last Exam (no tools, text-only) #4/13 47%

Text-only Humanity's Last Exam variant evaluated without tool use.

MathArena Apex #5/8 38.7%

MathArena Apex is a challenging math contest benchmark featuring the most difficult mathematical problems designed to test advanced reasoning and problem-solving abilities of AI models. It focuses on olympiad-level mathematics and complex multi-step mathematical reasoning.

HorizonMath #2/4 7.1%

HorizonMath is an extremely difficult frontier mathematics benchmark designed to test the limits of mathematical reasoning on research-level and competition-beyond problems.

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Hy3

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Hy3 open-source or proprietary?

Hy3 (hy3) is a proprietary commercial model by Tencent 腾讯混元. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Hy3?

Hy3 supports 262K input context and 128,000 max output tokens, priced at $0.132/1M input ($0.033/1M cached) and $0.528/1M output.