Qwen3.6 Plus

Leaderboards

Where Qwen3.6 Plus sits among the top 20 in each category.

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Test results

Every test Qwen3.6 Plus has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #25 / 256

  Graduate-level science questions written to be hard to look up.

  90.4%

  Self-reported

• MMLU-Pro

  #3 / 142

  Broad knowledge and reasoning across 14 subjects, ten answer choices each.

  88.5%

  Self-reported

• SWE-Bench Verified

  #20 / 120

  Fixing real bugs in real GitHub projects, checked by the projects' own tests.

  78.8%

  Self-reported

• Humanity's Last Exam

  #56 / 108

  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

  28.8%

  Self-reported · In the text score· In the vision score

• MMMU-Pro

  #18 / 73

  College-level questions that need both an image and text to answer.

  78.8%

  Self-reported · In the vision score

• IFEval

  #3 / 70

  Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints

  94.3%

  Self-reported

• LiveCodeBench v6

  #12 / 67

  LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

  87.1%

  Self-reported

• MMMU

  #1 / 66

  MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.

  86.0%

  Self-reported

• SWE-Bench Pro

  #34 / 61

  Harder, longer software engineering tasks from real codebases.

  56.6%

  Self-reported · In the coding score

• CharXiv-R

  #23 / 60

  Reading and reasoning about charts from scientific papers.

  81.5%

  Self-reported

• Terminal-Bench 2.0

  #19 / 54

  Getting real work done in a command-line terminal.

  61.6%

  Self-reported

• MMMLU

  #10 / 51

  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, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.

  89.5%

  Self-reported

• MMLU-Redux

  #3 / 50

  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.

  94.5%

  Self-reported

• SWE-bench Multilingual

  #18 / 49

  A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++. Contains 1,632 high-quality instances carefully annotated from 2,456 candidates by 68 expert annotators, designed to evaluate Large Language Models across diverse software ecosystems beyond Python.

  73.8%

  Self-reported

• IFBench

  #22 / 44

  Instruction Following Benchmark evaluating model's ability to follow complex instructions

  74.2%

  Self-reported

• Toolathlon

  #35 / 42

  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.

  39.8%

  Self-reported · In the agents score

• LiveBench

  #28 / 38

  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. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

  70.9%

  Self-reported · In the text score

• MCP Atlas

  #19 / 38

  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.

  74.1%

  Self-reported

• MathVision

  #9 / 38

  MATH-Vision is a dataset designed to measure multimodal mathematical reasoning capabilities. It focuses on evaluating how well models can solve mathematical problems that require both visual understanding and mathematical reasoning, bridging the gap between visual and mathematical domains.

  88.0%

  Self-reported

• SuperGPQA

  #2 / 37

  SuperGPQA is a comprehensive benchmark that evaluates large language models across 285 graduate-level academic disciplines. The benchmark contains 25,957 questions covering 13 broad disciplinary areas including Engineering, Medicine, Science, and Law, with specialized fields in light industry, agriculture, and service-oriented domains. It employs a Human-LLM collaborative filtering mechanism with over 80 expert annotators to create challenging questions that assess graduate-level knowledge and reasoning capabilities.

  71.6%

  Self-reported

• AI2D

  #2 / 35

  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. The benchmark evaluates diagram understanding and visual reasoning capabilities, requiring models to interpret diagrammatic elements, relationships, and structure to answer questions about scientific concepts represented in visual form.

  94.4%

  Self-reported

• HMMT 2025

  #5 / 33

  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

  96.7%

  Self-reported

• MMLU-ProX

  #3 / 32

  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.

  84.7%

  Self-reported

• RealWorldQA

  #8 / 32

  RealWorldQA is a benchmark designed to evaluate basic real-world spatial understanding capabilities of multimodal models. The initial release consists of over 700 anonymized images taken from vehicles and other real-world scenarios, each accompanied by a question and easily verifiable answer. Released by xAI as part of their Grok-1.5 Vision preview to test models' ability to understand natural scenes and spatial relationships in everyday visual contexts.

  85.4%

  Self-reported

• Include

  #4 / 31

  Include benchmark - specific documentation not found in official sources

  85.1%

  Self-reported

• ERQA

  #9 / 29

  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

  65.7%

  Self-reported

• Finance Agent v2

  #18 / 28

  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.

  40.8%

  Self-reported

• HMMT25

  #2 / 28

  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

  94.6%

  Self-reported

• OSWorld-Verified

  #23 / 28

  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.

  62.5%

  Self-reported

• VideoMMMU

  #10 / 28

  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. Contains 300 videos and 900 human-annotated questions spanning Art, Business, Science, Medicine, Humanities, and Engineering.

  84.0%

  Self-reported

• MMStar

  #1 / 27

  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. The benchmark addresses issues of visual content unnecessity and unintentional data leakage in existing multimodal evaluations.

  83.3%

  Self-reported

• ScreenSpot Pro

  #14 / 27

  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. The benchmark comprises 1,581 instructions across 23 applications spanning 5 industries and 3 operating systems, featuring authentic high-resolution images from professional domains with expert annotations. Unlike previous benchmarks that focus on cropped screenshots in consumer applications, ScreenSpot-Pro addresses the complexity and diversity of real-world professional software scenarios, revealing significant performance gaps in current MLLM GUI perception capabilities.

  68.2%

  Self-reported

• AIME 2026

  #6 / 26

  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. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

  95.3%

  Self-reported

• AA-LCR

  #11 / 25

  Agent Arena Long Context Reasoning benchmark

  68.3%

  Self-reported

• NL2Repo

  #23 / 25

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

  37.9%

  Self-reported · In the coding score

• LongBench v2

  #3 / 24

  LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.

  62.0%

  Self-reported

• WMT24++

  #5 / 24

  WMT24++ is a comprehensive multilingual machine translation benchmark that expands the WMT24 dataset to cover 55 languages and dialects. It includes human-written references and post-edits across four domains (literary, news, social, and speech) to evaluate machine translation systems and large language models across diverse linguistic contexts.

  84.3%

  Self-reported

• PolyMATH

  #3 / 23

  Polymath is a challenging multi-modal mathematical reasoning benchmark designed to evaluate the general cognitive reasoning abilities of Multi-modal Large Language Models (MLLMs). The benchmark comprises 5,000 manually collected high-quality images of cognitive textual and visual challenges across 10 distinct categories, including pattern recognition, spatial reasoning, and relative reasoning.

  77.4%

  Self-reported

• IMO-AnswerBench

  #12 / 22

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

  83.8%

  Self-reported

• C-Eval

  #2 / 20

  C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.

  93.3%

  Self-reported

• OmniDocBench 1.5

  #3 / 20

  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. Lower Overall Edit Distance scores are better.

  91.2%

  Self-reported

• CC-OCR

  #1 / 18

  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. Contains 39 subsets with 7,058 fully annotated images, 41% sourced from real applications. Tests capabilities including text grounding, multi-orientation text recognition, and detecting hallucination/repetition across diverse visual challenges.

  83.4%

  Self-reported

• SimpleVQA

  #10 / 17

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

  0.7%

  Self-reported

• Video-MME

  #8 / 17

  Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in video analysis. It features 900 videos totaling 254 hours with 2,700 human-annotated question-answer pairs across 6 primary visual domains (Knowledge, Film & Television, Sports Competition, Life Record, Multilingual, and others) and 30 subfields. The benchmark evaluates models across diverse temporal dimensions (11 seconds to 1 hour), integrates multi-modal inputs including video frames, subtitles, and audio, and uses rigorous manual labeling by expert annotators for precise assessment.

  84.2%

  Self-reported

• FrontierSWE

  #16 / 16

  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.

  22.0%

  Self-reported

• ODinW

  #1 / 16

  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

  51.8%

  Self-reported

• Global PIQA

  #5 / 15

  Global PIQA is a multilingual commonsense reasoning benchmark that evaluates physical interaction knowledge across 100 languages and cultures. It tests AI systems' understanding of physical world knowledge in diverse cultural contexts through multiple choice questions about everyday situations requiring physical commonsense.

  89.8%

  Self-reported

• Claw-Eval

  #12 / 14

  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.

  58.7%

  Self-reported

• WideSearch

  #6 / 14

  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.

  74.3%

  Self-reported

• HMMT Feb 26

  #8 / 13

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

  87.8%

  Self-reported

• MAXIFE

  #3 / 12

  MAXIFE is a multilingual benchmark evaluating LLMs on instruction following and execution across multiple languages and cultural contexts.

  88.2%

  Self-reported

• NOVA-63

  #6 / 12

  NOVA-63 is a multilingual evaluation benchmark covering 63 languages, designed to assess LLM performance across diverse linguistic contexts and tasks.

  57.9%

  Self-reported

• VITA-Bench

  #4 / 11

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

  44.3%

  Self-reported

• DeepPlanning

  #2 / 10

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

  41.5%

  Self-reported

• MLVU

  #3 / 10

  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.

  86.7%

  Self-reported

• SkillsBench

  #7 / 10

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

  45.7%

  Self-reported

• CountBench

  #5 / 9

  CountBench evaluates object counting capabilities in visual understanding.

  1.0%

  Self-reported

• DynaMath

  #1 / 9

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

  88.0%

  Self-reported

• MCP-Mark

  #5 / 9

  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.

  48.2%

  Self-reported

• RefCOCO-avg

  #1 / 9

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

  0.9%

  Self-reported

• TAU3-Bench

  #2 / 8

  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.

  70.7%

  Self-reported

• MMLongBench-Doc

  #2 / 7

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

  0.6%

  Self-reported

• V*

  #1 / 7

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

  96.9%

  Self-reported

• TIR-Bench

  #1 / 4

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

  61.6%

  Self-reported

• We-Math

  #1 / 1

  We-Math evaluates multimodal models on visual mathematical reasoning, requiring models to understand and solve math problems presented with visual elements such as diagrams, charts, and geometric figures.

  89.0%

  Unverified