AI Models Finder

Hunyuan T1 20250403

Hunyuan T1 20250403

A deep inference optimization model developed by Tencent, based on the Hybrid-Transformer-Mamba MoE architecture, which enhances the ability to handle mathematical logic and complex tasks.

Intelligence(Medium)

Speed(Slow)

Input Supported Modalities

No

Is Reasoning Model

64,000

Context Window

64,000

Maximum Output Tokens

2024-12-31

Knowledge Cutoff

Pricing

￥1 /M tokens

Input

￥4 /M tokens

Output

￥3 /M tokens

Blended Price

Quick Simple Comparison

Input

Output

Hunyuan-T1-20250403

￥0.14

Hunyuan-Vision

￥2.5

HunYuan-TurboS

￥0.11

Basic Parameters

Hunyuan-T1-20250403Technical Parameters

Parameter Count

Not Announced

Context Length

64.00k tokens

Training Data Cutoff

2024-12-31

Open Source Category

Proprietary

Multimodal Support

Text Only

Throughput

1,580

Release Date

2025-04-03

Response Speed

21.4 tokens/s

Benchmark Scores

Below is the performance of Hunyuan-T1-20250403 in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

52.1

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

71.6

Indicator of AI model performance on coding tasks

Math Index

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

78.9

Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks

MMLU Pro

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

82.9

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

-

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

-

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

6490

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

-

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

76.8

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

9620

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

7820

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

Input tokens/million

Output tokens/million

Input tokens/million

Output tokens/million

Input tokens/million

Output tokens/million

Input tokens/million

Output tokens/million

Input tokens/million

Output tokens/million

Gemini 2.0 Flash Lite (Preview)

Input tokens/million

Output tokens/million

Input tokens/million

Output tokens/million

Qwen2.5 Coder Instruct 32B

Input tokens/million

Output tokens/million

AIbase

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

© 2025AIbase