मुख्य सामग्री पर जाएं
AITier

Qwen3.5 122B A10B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

विवरण

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.

रिलीज़ तिथि
2026-02-24
पैरामीटर
122.0B
संदर्भ लंबाई
262K
मोडैलिटीज़
image, text, video

क्षमता रडार

31
general
32
coding
83
reasoning
53
scienceअनुमानित
60
agents
80
multimodal

समर्पित विज्ञान बेंचमार्क उपलब्ध न होने पर Science तर्क प्रॉक्सी का उपयोग करके अनुमान लगाता है।

रैंकिंग

डोमेन#रैंकस्कोरस्रोत
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

बेंचमार्क स्कोर (LLM Stats)

3d

SUNRGBD0.36 / 100स्वयं
Hypersim0.13 / 100स्वयं

Agents

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

Biology

GPQA86.6%स्वयं

Chemistry

SuperGPQA67.1%स्वयं

Code

SWE-Bench Verified72.0%स्वयं

Communication

Multi-Challenge61.5%स्वयं

Embodied

EmbSpatialBench0.84 / 100स्वयं

Finance

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

General

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

Grounding

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

Healthcare

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

Image To Text

OCRBench92.1%स्वयं

Language

LingoQA80.8%स्वयं
WMT24++78.3%स्वयं

Long Context

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

Math

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

Multimodal

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

Reasoning

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

Spatial Reasoning

RealWorldQA85.1%स्वयं

Vision

ODinW44.5%स्वयं

AA मूल्यांकन सूचकांक

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

LLM Stats श्रेणी स्कोर

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

मूल्य निर्धारण

इनपुट मूल्य$0.4 / 1M tokens
आउटपुट मूल्य$3.2 / 1M tokens
मिश्रित मूल्य (3:1)$1.1 / 1M tokens

गति

टोकन/सेकंड146.3 tokens/s
पहले टोकन में देरी1.23s
पहले उत्तर में देरी1.23s

उपलब्ध प्रदाता

(LS आंतरिक इकाइयाँ)
प्रदाताइनपुट मूल्यआउटपुट मूल्य
Novita400K3.2M

बाहरी लिंक

LLM Stats