Skip to main content
AITier

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
audio, image, text, video

Capability Radar

26
general
42
coding
83
reasoning
53
science
60
agents
80
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability79
45.0
LS
Code Ranking184
57.0
AA
General Ranking193
57.0
AA
Multimodal Ranking24
59.0
LS
Science181
57.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

3d

SUNRGBD0.36 / 100SR
Hypersim0.13 / 100SR

Agents

t2-bench79.5%SR
BFCL-V472.2%SR
AndroidWorld_SR66.4%SR
BrowseCompOpenAI (2025)63.8%SR
FullStackBench en62.6%SR
WideSearch60.5%SR
FullStackBench zh58.7%SR
OSWorld-Verified58.0%SR
TIR-Bench53.2%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)49.4%SR
VITA-Bench33.6%SR
DeepPlanning24.1%SR

Biology

GPQANYU + Cohere + Anthropic (2023)86.6%SR

Chemistry

SuperGPQA67.1%SR

Code

SWE-Bench Verified72.0%SR

Communication

Multi-Challenge61.5%SR

Embodied

EmbSpatialBench0.84 / 100SR

Finance

MMLU-Pro86.7%SR
MMLU-ProX82.2%SR

General

MMLU-Redux94.0%SR
IFEvalGoogle Research (2023)93.4%SR
C-Eval91.9%SR
Global PIQA88.4%SR
MAXIFE87.9%SR
MMMLU86.7%SR
MMMU83.9%SR
MMStar82.9%SR
Include82.8%SR
LiveCodeBench v678.9%SR
MMMU-Pro76.9%SR
IFBench76.1%SR
SimpleVQA0.62 / 100SR
LongBench v260.2%SR
NOVA-6358.6%SR

Grounding

RefCOCO-avg0.91 / 100SR
ScreenSpot Pro70.4%SR
RefSpatialBench0.69 / 100SR

Healthcare

VideoMMMU82.0%SR
SlakeVQA81.6%SR
MedXpertQA67.3%SR
PMC-VQA63.3%SR

Image To Text

OCRBench92.1%SR

Language

LingoQA80.8%SR
WMT24++78.3%SR

Long Context

MLVU87.3%SR
LVBench74.4%SR
AA-LCR66.9%SR
MMLongBench-Doc0.59 / 100SR

Math

HMMT 202591.4%SR
HMMT2590.3%SR
MathVista-Mini87.4%SR
MathVision86.2%SR
DynaMath85.9%SR
CodeForces0.85 / 3000SR
PolyMATH68.9%SR
Humanity's Last Exam47.5%SR

Multimodal

VLMsAreBlind96.7%SR
AI2D93.3%SR
V*93.2%SR
MMBench-V1.192.8%SR
OmniDocBench 1.589.8%SR
VideoMME w sub.87.3%SR
VideoMME w/o sub.83.9%SR
CC-OCR81.8%SR
CharXiv-R77.2%SR
MVBench76.6%SR
MMVU74.7%SR
BabyVision40.2%SR
ZEROBench-Sub0.36 / 100SR
Nuscene15.4%SR
ZEROBench0.09 / 100SR

Reasoning

CountBench0.97 / 100SR
BrowseComp-zh69.9%SR
Hallusion Bench67.6%SR
ERQA62.0%SR
Seal-044.1%SR
OJBench39.5%SR

Spatial Reasoning

RealWorldQA85.1%SR

Vision

ODinW44.5%SR

AA Evaluation Indices

(Artificial Analysis)
Coding Index(Artificial Analysis)
43.3
Intelligence Index(Artificial Analysis)
28.2
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Lcr(Artificial Analysis)
0.6
Ifbench(Google Research (2023))
0.5
Terminalbench V2 1
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench Hard(Stanford × Laude Institute (2026))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.2
Tau Banking
0.1

LLM Stats Category Scores

(LLM Stats (zeroeval))
Biology
90
Legal
80
Math
80
Physics
80
Structured Output
80
Image To Text
80
Instruction Following
80
Language
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)$1.1 / 1M tokens

Speed

Tokens/sec148.9
Time to First Token1.03s
Time to Answer1.03s

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: AlibabaMost Expensive: Cortecs
ProviderInputOutput
1AlibabaPRIMARY
$0.4
$3.2
2NanoGPT
$0.437
$3.496
3Cortecs
$0.495
$3.46

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis