NOUMENOpen app
NOUMEN

tencent · Efficient

Tencent Hy3

Added Jul 6, 2026

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Hy3 is Tencent's 295B-parameter Mixture-of-Experts model with 21B active parameters, native 256K context, and configurable reasoning modes. It is built for coding, long-context comprehension, multi-turn dialogue, and agentic task execution with a focus on high-throughput production workloads.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
none · low · high
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.066
Output
$0.26
Cache read
$0.029

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
128K
Average output (7 days)
1.4K tokens
Longer than 83% of 468 models

Side by side

Compare models

Put Tencent Hy3 next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryInklingGrok 4.20Kimi K2.7 Code TEEAll 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

25.3

Better than 62% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    58.8

    Composite of the coding evaluations

    Better than 60% of 168 scored models

Agentic work

  • AutomationBench-AA

    18.4%

    Workflow automation, penalized for guardrail violations

    Better than 38% of 173 scored models

  • AutomationBench-AA tasks completed

    2.7%

    Workflows finished end to end without a guardrail violation

    Better than 39% of 173 scored models

  • AA-Briefcasev1.1

    947 Elo

    Agentic knowledge work, rated head to head

    Better than 42% of 166 scored models

  • GDPval-AAv2.1

    1,063 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 42% of 187 scored models

Document reasoning

  • GDP.pdf

    11.2%

    Professional reasoning over PDF documents, all-pass rate

    Better than 47% of 171 scored models

  • AA-LCRv1.1

    79.0%

    Reasoning across long documents

    Better than 72% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    33.5%

    Expert-level questions across academic fields

    Better than 67% of 323 scored models

  • GPQA Diamond

    89.7%

    Graduate-level science questions

    Better than 77% of 291 scored models

Coding

  • Terminal-Benchv4.0

    0.5%

    Practical software engineering in a terminal

    Better than 30% of 171 scored models

  • SciCode

    48.6%

    Scientific computing in Python

    Better than 45% of 174 scored models

Legacy evaluations

  • AA-LCR (unversioned)

    79.0%

    Long-context reasoning, earlier grading

    Better than 72% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
72.3 tok/s
Faster than 49% of 253 models
Time to first token
3.7 s
Quicker than 48% of 253 models
Prompt cache hits
68.8%
About $0.0406 per 1M input tokens with caching
Request success (24h)
99.5%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 98.2%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy3",
    "reasoning_effort": "none",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="tencent/hy3",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

tencent

Other tencent models, starting with the same family.