Venice Atlas
← Back to model catalog

VENICE ATLAS · MODEL DOSSIER · QWEN 3.6 PLUS UNCENSORED

Model overview

Qwen 3.6 Plus Uncensored

Qwen 3.6 Plus Uncensored is Alibaba's latest flagship reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.

qwen-3-6-plus · venice.ai
Text · Venice catalog$0.63 per 1M tokensPrice on Venice AI
ModalityTextOn Venice AI
Primary price$0.63 per 1M tokensper 1M tokens
Context window1MMax tokens
Benchmarks65Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Biology#2232.59 ratingChat#427.37 ratingChemistry#1037.53 ratingEconomics#227.02 ratingVision#3728.46 ratingFinance#337.06 ratingFrontend Development#1425.41 ratingGrounding#620.24 ratingHealthcare#342.00 ratingImage To Text#1017.51 ratingInstruction Following#726.65 ratingLanguage#338.51 ratingLegal#340.91 ratingLong Context#925.04 ratingMath#1539.10 ratingMultimodal#2731.08 ratingPhysics#1037.57 ratingSearch#2416.77 ratingSpatial Reasoning#1027.55 ratingStructured Output#133.92 ratingText To Image#123.29 ratingVideo understanding#920.62 rating
Agents6 results
DeepPlanningdeep-planning · agents
41.5%
ReportedOct 2026
Finance Agent v2finance-agent-v2 · agents
40.8%
ReportedOct 2026
MCP-Markmcp-mark · agents
48.2%
ReportedOct 2026
TAU3-Benchtau3-bench · agents
70.7%
ReportedOct 2026
Toolathlontoolathlon · agents
39.8%
ReportedOct 2026
VITA-Benchvita-bench · agents
44.3%
ReportedOct 2026
Chat1 result
IFEvalifeval · chat
94.3%
ReportedOct 2026
Coding4 results
Claw-Evalclaw-eval · code
58.7%
ReportedOct 2026
FrontierSWEfrontierswe · code
22.0%
ReportedOct 2026
NL2Reponl2repo · code
37.9%
ReportedOct 2026
SkillsBenchskillsbench · code
45.7%
ReportedOct 2026
General intelligence4 results
C-Evalc-eval · general
93.3%
ReportedOct 2026
Includeinclude · general
85.1%
ReportedOct 2026
MAXIFEmaxife · general
88.2%
ReportedOct 2026
NOVA-63nova-63 · general
57.9%
ReportedOct 2026
Instruction Following1 result
IFBenchifbench · instruction_following
74.2%
ReportedOct 2026
Language5 results
MMLU-Prommlu-pro · language
88.5%
ReportedOct 2026
MMLU-ProXmmlu-prox · language
84.7%
ReportedOct 2026
MMLU-Reduxmmlu-redux · language
94.5%
ReportedOct 2026
MMMLUmmmlu · language
89.5%
ReportedOct 2026
WMT24++wmt24++ · language
84.3%
ReportedOct 2026
Long Context1 result
LongBench v2longbench-v2 · long_context
62.0%
ReportedOct 2026
Math8 results
AIME 2026aime-2026 · math
95.3%
ReportedOct 2026
DynaMathdynamath · math
88.0%
ReportedOct 2026
HMMT 2025hmmt-2025 · math
96.7%
ReportedOct 2026
HMMT Feb 26hmmt-feb-26 · math
87.8%
ReportedOct 2026
HMMT25hmmt25 · math
94.6%
ReportedOct 2026
IMO-AnswerBenchimo-answerbench · math
83.8%
ReportedOct 2026
LiveBenchlivebench · math
70.9%
ReportedOct 2026
MathVisionmathvision · math
88.0%
ReportedOct 2026

Learn what each benchmark measures ↗

Related models

More from qwen

qwen-3-7-plusQwen 3.7 Plus$0.50 input per 1M tokens ↗qwen-3-8-flashQwen 3.8 Flash$0.14 input per 1M tokens ↗qwen3-5-35b-a3bQwen 3.5 35B A3B$0.15 input per 1M tokens ↗