Skip to main content

Qwen3.5 122B A10B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3.5-122B-A10B is a multimodal Mixture-of-Experts model with 122 billion total parameters and 10 billion activated parameters. It combines strong reasoning, coding, long-context, and visual understanding performance with production-friendly efficiency and a native 262K context window.

Release Date
2026-02-24
Parameters
122.0B
Context Length
262K
Modalities
image, text, video

Capability Radar

70
general
60
coding
80
reasoning
77
scienceest.
60
agents
80
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Agentic Capability59
50.0
LS
Multimodal Ranking49
58.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench79.5%SR
VITA-Bench33.6%SR
DeepPlanning24.1%SR

Chat

IFEvalGoogle Research (2023)93.4%SR
Multi-Challenge61.5%SR

Code

FullStackBench en62.6%SR
FullStackBench zh58.7%SR

General

C-Eval91.9%SR
MAXIFE87.9%SR
Include82.8%SR
AndroidWorld_SR66.4%SR
NOVA-6358.6%SR

Healthcare

MedXpertQA67.3%SR
PMC-VQA63.3%SR

Instruction Following

IFBench76.1%SR

Language

MMLU-Redux94.0%SR
MMMLU86.7%SR
MMLU-Pro86.7%SR
MMLU-ProX82.2%SR
WMT24++78.3%SR

Long Context

LongBench v260.2%SR

Math

HMMT 202591.4%SR
HMMT2590.3%SR
MathVista-Mini87.4%SR
MathVision86.2%SR
DynaMath85.9%SR
CodeForces0.85 / 3000SR
PolyMATH68.9%SR

Multimodal

VideoMME w/o sub.83.9%SR
MMMU83.9%SR
VideoMMMU82.0%SR
OSWorld-Verified58.0%SR
TIR-Bench53.2%SR

Reasoning

Global PIQA88.4%SR
GPQANYU + Cohere + Anthropic (2023)86.6%SR
LiveCodeBench v678.9%SR
CharXiv-R77.2%SR
SWE-Bench Verified72.0%SR
BrowseComp-zh69.9%SR
SuperGPQA67.1%SR
AA-LCR66.9%SR
BrowseCompOpenAI (2025)63.8%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)49.4%SR
Humanity's Last Exam47.5%SR
Seal-044.1%SR
OJBench39.5%SR

Search

WideSearch60.5%SR

Tool Calling

BFCL-V472.2%SR

Video

MLVU87.3%SR

Vision

CountBench0.97 / 100SR
VLMsAreBlind96.7%SR
AI2D93.3%SR
V*93.2%SR
MMBench-V1.192.8%SR
OCRBench92.1%SR
RefCOCO-avg0.91 / 100SR
OmniDocBench 1.589.8%SR
VideoMME w sub.87.3%SR
RealWorldQA85.1%SR
EmbSpatialBench0.84 / 100SR
MMStar82.9%SR
CC-OCR81.8%SR
SlakeVQA81.6%SR
LingoQA80.8%SR
MMMU-Pro76.9%SR
MVBench76.6%SR
MMVU74.7%SR
LVBench74.4%SR
ScreenSpot Pro70.4%SR
RefSpatialBench0.69 / 100SR
Hallusion Bench67.6%SR
ERQA62.0%SR
SimpleVQA0.62 / 100SR
MMLongBench-Doc0.59 / 100SR
ODinW44.5%SR
BabyVision40.2%SR
SUNRGBD0.36 / 100SR
ZEROBench-Sub0.36 / 100SR
Nuscene15.4%SR
Hypersim0.13 / 100SR
ZEROBench0.09 / 100SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Biology
90
Chat
80
Image To Text
80
Instruction Following
80
Language
80
Legal
80
Math
80
Physics
80
Structured Output
80
Embodied
80
Finance
80
Grounding
80
Healthcare
80
Chemistry
80
Text-to-image
80
Video
80
Long Context
70
Multimodal
70
Reasoning
70
Spatial Reasoning
70
Frontend Development
70
General
70
Economics
70
Vision
70
Search
60
Agents
60
Code
60
Communication
60
Tool Calling
60
Spatial
20
3d
20

Pricing

Input Price$0.4 / 1M tokens
Output Price$3.2 / 1M tokens
Blended Price (3:1)$0.8175 / 1M tokens

Speed

Tokens/sec142.4
Time to First Token2.30s
Time to Answer2.30s

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: DeepInfraMost Expensive: Alibaba
ProviderInputOutput
1DeepInfraCheapest
$0.29
$2.4
2AlibabaPRIMARY
$0.4
$3.2

Compare pricing across different API providers for this model.

External Sources