Passer au contenu principal
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.

Date de sortie
2026-02-24
Paramètres
122.0B
Longueur du contexte
262K
Modalités
image, text, video

Radar de capacités

31
general
32
coding
83
reasoning
53
scienceest.
60
agents
80
multimodal

Science utilise un proxy de raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.

Classements

Domaine#RangScoreSource
Agents & Tools45
58.0
LS
Code Ranking116
57.0
AA
General Ranking121
63.0
AA
Multimodal Ranking61
70.0
LS
Reasoning53
68.0
LS
Science108
59.0
AA

Scores de benchmarks (LLM Stats)

3d

SUNRGBD0.36 / 100Aut.
Hypersim0.13 / 100Aut.

Agents

t2-bench79.5%Aut.
BFCL-V472.2%Aut.
AndroidWorld_SR66.4%Aut.
BrowseComp63.8%Aut.
FullStackBench en62.6%Aut.
WideSearch60.5%Aut.
FullStackBench zh58.7%Aut.
OSWorld-Verified58.0%Aut.
TIR-Bench53.2%Aut.
Terminal-Bench 2.049.4%Aut.
VITA-Bench33.6%Aut.
DeepPlanning24.1%Aut.

Biology

GPQA86.6%Aut.

Chemistry

SuperGPQA67.1%Aut.

Code

SWE-Bench Verified72.0%Aut.

Communication

Multi-Challenge61.5%Aut.

Embodied

EmbSpatialBench0.84 / 100Aut.

Finance

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

General

MMLU-Redux94.0%Aut.
IFEval93.4%Aut.
C-Eval91.9%Aut.
Global PIQA88.4%Aut.
MAXIFE87.9%Aut.
MMMLU86.7%Aut.
MMMU83.9%Aut.
MMStar82.9%Aut.
Include82.8%Aut.
LiveCodeBench v678.9%Aut.
MMMU-Pro76.9%Aut.
IFBench76.1%Aut.
SimpleVQA0.62 / 100Aut.
LongBench v260.2%Aut.
NOVA-6358.6%Aut.

Grounding

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

Healthcare

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

Image To Text

OCRBench92.1%Aut.

Language

LingoQA80.8%Aut.
WMT24++78.3%Aut.

Long Context

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

Math

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

Multimodal

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

Reasoning

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

Spatial Reasoning

RealWorldQA85.1%Aut.

Vision

ODinW44.5%Aut.

Indices d'évaluation AA

Intelligence Index
35.9
Coding Index
31.6
Tau2
0.8
Gpqa
0.8
Lcr
0.6
Ifbench
0.5
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.1

Scores par catégorie LLM Stats

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

Tarification

Prix d'entrée$0.4 / 1M tokens
Prix de sortie$3.2 / 1M tokens
Prix mixte (3:1)$1.1 / 1M tokens

Vitesse

Tokens/sec146.3 tokens/s
Délai du premier token1.23s
Temps de réponse1.23s

Fournisseurs disponibles

(Unités internes LS)
FournisseurPrix d'entréePrix de sortie
Novita400K3.2M

Sources externes

LLM Stats