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
Alibaba Qwen
Proprietary API Alibaba Qwen · qwen3.6-plus · Text+Image+Video

Qwen3.6 Plus Official Specifications, Pricing & Benchmarks

Qwen3.6 Plus (qwen3.6-plus) by Alibaba Qwen, released 2026-04-02, featuring 1,000,000 context window, 65,536 max output tokens, and Text+Image+Video input.

📋 Qwen3.6 Plus Official API & System Card Specifications

Verified against official Alibaba Qwen developer documentation & pricing

API Model ID: qwen3.6-plus

1. Identity & Capabilities

API Spec
API Model ID
qwen3.6-plus
Release Date
2026-04-02
Weight License
Proprietary (Undisclosed)
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
1,000,000 tokens (1000K)
Max Output Tokens
65,536 tokens
Input Modalities
Text + Image + Video
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.5
Cached Input / 1M
$ 0.05 -90%
Output / 1M Tokens
$ 3
Tiered Pricing Notes

🎛️ 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

📊 Qwen3.6 Plus Full Benchmark Scorecard

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

⚔️ Compare head-to-head

💻 Coding 9 items

SWE-Bench Verified #17/59 78.8%

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.

MCP Atlas #21/39 74.1%

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 Multilingual #17/33 73.8%

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

Terminal-Bench 2.0 #17/38 61.6%

Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal.

Claw-Eval #12/13 58.7%

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 #31/52 56.6%

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 #7/11 45.7%

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

NL2Repo #20/23 37.9%

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

FrontierSWE #15/16 22%

FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

🤖 Agents & Tools 9 items

WideSearch #5/13 74.3%

WideSearch is an agentic search benchmark that evaluates models' ability to perform broad, parallel search operations across multiple sources. It tests wide-coverage information retrieval and synthesis capabilities.

TAU3-Bench #2/6 70.7%

TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities, testing models on multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.

OSWorld-Verified #21/26 62.5%

OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.

TIR-Bench #1/4 61.6%

A tool-calling and multimodal interaction benchmark for testing visual instruction following and execution reliability.

MCP-Mark #5/7 48.2%

MCP-Mark evaluates LLMs on their ability to use Model Context Protocol (MCP) tools effectively, testing tool discovery, selection, invocation, and result interpretation across diverse MCP server scenarios.

VITA-Bench #4/8 44.3%

VITA-Bench evaluates AI agents on real-world virtual task automation, measuring their ability to complete complex multi-step tasks in simulated environments.

DeepPlanning #2/7 41.5%

DeepPlanning evaluates LLMs on complex multi-step planning tasks requiring long-horizon reasoning, goal decomposition, and strategic decision-making.

Finance Agent v2 #17/27 40.9%

Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

Toolathlon #28/32 39.8%

Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.

📐 Math 15 items

HMMT 2025 #1/11 96.7%

Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds.

AIME 2026 #5/18 95.3%

All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999.

HMMT25 #1/9 94.6%

Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds.

MMLU-Redux #3/15 94.5%

An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.

MMMLU #6/20 89.5%

Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili…

MMLU-Pro #2/39 88.5%

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

MathVision #9/20 88%

MATH-Vision is a dataset designed to measure multimodal mathematical reasoning capabilities.

DynaMath #1/8 88%

A multimodal mathematics and reasoning benchmark focused on dynamic visual problem solving.

HMMT Feb 26 #7/11 87.8%

HMMT February 2026 is a math competition benchmark based on problems from the Harvard-MIT Mathematics Tournament, testing advanced mathematical problem-solving and reasoning.

MMLU-ProX #3/13 84.7%

Extended version of MMLU-Pro providing additional challenging multiple-choice questions for evaluating language models across diverse academic and professional domains. Built on the foundation of the Massive Multitask Language Understanding benchmark framework.

IMO-AnswerBench #10/17 83.8%

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

PolyMATH #3/9 77.4%

Polymath is a challenging multi-modal mathematical reasoning benchmark designed to evaluate the general cognitive reasoning abilities of Multi-modal Large Language Models (MLLMs).

SuperGPQA #2/16 71.6%

SuperGPQA is a comprehensive benchmark that evaluates large language models across 285 graduate-level academic disciplines.

LiveBench #20/27 70.9%

LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.

Humanity's Last Exam #44/69 28.8%

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.

👁️ Multimodal 19 items

V* #1/7 96.9%

A visual reasoning benchmark evaluating multimodal inference under challenging spatial and grounded tasks.

AI2D #1/7 94.4%

AI2D is a dataset of 4,903 illustrative diagrams from grade school natural sciences (such as food webs, human physiology, and life cycles) with over 15,000 multiple choice questions and answers.

OmniDocBench 1.5 #3/16 91.2%

OmniDocBench 1.5 is a comprehensive benchmark for evaluating multimodal large language models on document understanding tasks, including OCR, document parsing, information extraction, and visual question answering across diverse document types.

MLVU #3/7 86.7%

A comprehensive benchmark for multi-task long video understanding that evaluates multimodal large language models on videos ranging from 3 minutes to 2 hours across 9 distinct tasks including reasoning, captioning, recognition, and summarization.

MMMU #1/16 86%

MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning.

RealWorldQA #6/13 85.4%

RealWorldQA is a benchmark designed to evaluate basic real-world spatial understanding capabilities of multimodal models.

Video-MME #8/8 84.2%

Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in video analysis.

VideoMMMU #7/14 84%

Video-MMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through three cognitive stages: perception, comprehension, and adaptation.

CC-OCR #1/6 83.4%

A comprehensive OCR benchmark for evaluating Large Multimodal Models (LMMs) in literacy. Comprises four OCR-centric tracks: multi-scene text reading, multilingual text reading, document parsing, and key information extraction.

MMStar #1/8 83.3%

MMStar is an elite vision-indispensable multimodal benchmark comprising 1,500 challenge samples meticulously selected by humans to evaluate 6 core capabilities and 18 detailed axes.

CharXiv-R #21/41 81.5%

CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements.

MMMU-Pro #15/44 78.8%

A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings.

ScreenSpot Pro #10/10 68.2%

ScreenSpot-Pro is a novel GUI grounding benchmark designed to rigorously evaluate the grounding capabilities of multimodal large language models (MLLMs) in professional high-resolution computing environments.

ERQA #6/13 65.7%

Embodied Reasoning Question Answering benchmark consisting of 400 multiple-choice visual questions across spatial reasoning, trajectory reasoning, action reasoning, state estimation, and multi-view reasoning for evaluating AI capabilities in physical world interactions.

ODinW #1/7 51.8%

Object Detection in the Wild (ODinW) benchmark for evaluating object detection models' task-level transfer ability across diverse real-world datasets in terms of prediction accuracy and adaptation efficiency.

CountBench #5/7 1

CountBench evaluates object counting capabilities in visual understanding.

RefCOCO-avg #1/6 0.9

RefCOCO-avg measures object grounding accuracy averaged across RefCOCO, RefCOCO+, and RefCOCOg benchmarks.

SimpleVQA #8/13 0.7

SimpleVQA is a visual question answering benchmark focused on simple queries.

MMLongBench-Doc #2/6 0.6

MMLongBench-Doc evaluates long document understanding capabilities in vision-language models.

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

Closest Self-Hostable Open-Weight Alternatives to Qwen3.6 Plus

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

Compare with these →

Frequently Asked Questions

Is Qwen3.6 Plus open-source or proprietary?

Qwen3.6 Plus (qwen3.6-plus) is a proprietary commercial model by Alibaba Qwen. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Qwen3.6 Plus?

Qwen3.6 Plus supports 1000K input context and 65,536 max output tokens, priced at $0.5/1M input ($0.05/1M cached) and $3/1M output.