AI Models Finder

Wan2.2

Wan2.2

Alibaba's newly open - sourced large - scale video generation model supports tasks such as text - to - video, image - to - video, and text - image - to - video. It uses the MoE architecture and has movie - level aesthetics and the ability to generate high - efficiency 720P@24fps videos.

Intelligence(Weak)

Speed(Slow)

Input Supported Modalities

Yes

Is Reasoning Model

131,072

Context Window

8,192

Maximum Output Tokens

-

Knowledge Cutoff

Pricing

- /M tokens

Input

- /M tokens

Output

- /M tokens

Blended Price

Quick Simple Comparison

Input

Output

Qwen2.5 Turbo

Qwen Turbo

Wan2.2

Basic Parameters

Wan2.2Technical Parameters

Parameter Count

Not Announced

Context Length

131.07k tokens

Training Data Cutoff

Open Source Category

Open Source

Multimodal Support

Text, Image

Throughput

0

Release Date

2025-07-28

Response Speed

0 tokens/s

Benchmark Scores

Below is the performance of Wan2.2 in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.

Intelligence Index

Large Language Model Intelligence Level

-

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

-

Indicator of AI model performance on coding tasks

Math Index

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

-

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

-

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

-

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

-

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

-

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)

-

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