Passer au contenu principal
AITier

Qwen3.5 397B A17B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3.5-397B-A17B is Qwen's flagship Mixture-of-Experts model with 397 billion total parameters and 17 billion activated parameters. It delivers state-of-the-art performance across knowledge, reasoning, coding, mathematics, multilingual understanding, instruction following, long context, and agent tasks.

Date de sortie
2026-02-16
Paramètres
397.0B
Longueur du contexte
262K
Modalités
image, text, video

Radar de capacités

36
general
38
coding
86
reasoning
57
scienceest.
60
agents
70
multimodal

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

Classements

Domaine#RangScoreSource
Agents & Tools41
59.0
LS
Code Ranking76
66.0
AA
General Ranking95
67.0
AA
Reasoning66
58.0
LS
Science67
67.0
AA

Scores de benchmarks (LLM Stats)

Agents

t2-bench86.7%Aut.
WideSearch74.0%Aut.
BFCL-V472.9%Aut.
BrowseComp69.0%Aut.
Terminal-Bench 2.052.5%Aut.
VITA-Bench49.7%Aut.
MCP-Mark46.1%Aut.
Toolathlon38.3%Aut.
DeepPlanning34.3%Aut.

Biology

GPQA88.4%Aut.

Chemistry

SuperGPQA70.4%Aut.

Code

SWE-Bench Verified76.4%Aut.
SWE-bench Multilingual69.3%Aut.

Coding

SecCodeBench68.3%Aut.

Communication

Multi-Challenge67.6%Aut.

Finance

MMLU-Pro87.8%Aut.
MMLU-ProX84.7%Aut.

General

MMLU-Redux94.9%Aut.
C-Eval93.0%Aut.
IFEval92.6%Aut.
Global PIQA89.8%Aut.
MMMLU88.5%Aut.
MAXIFE88.2%Aut.
Include85.6%Aut.
LiveCodeBench v683.6%Aut.
IFBench76.5%Aut.
LongBench v263.2%Aut.
NOVA-6359.1%Aut.

Language

WMT24++78.9%Aut.

Long Context

AA-LCR68.7%Aut.

Math

HMMT 202594.8%Aut.
HMMT2592.7%Aut.
AIME 202691.3%Aut.
IMO-AnswerBench80.9%Aut.
PolyMATH73.3%Aut.
Humanity's Last Exam28.7%Aut.

Reasoning

BrowseComp-zh70.3%Aut.
Seal-046.9%Aut.

Indices d'évaluation AA

Intelligence Index
40.1
Coding Index
37.4
Gpqa
0.9
Tau2
0.8
Lcr
0.6
Ifbench
0.5
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.2

Scores par catégorie LLM Stats

Biology
90
Language
90
Structured Output
80
Chemistry
80
Finance
80
Frontend Development
80
General
80
Healthcare
80
Instruction Following
80
Legal
80
Math
80
Physics
80
Spatial Reasoning
70
Code
70
Communication
70
Economics
70
Long Context
70
Multimodal
70
Reasoning
70
Search
70
Tool Calling
60
Agents
60
Vision
50

Tarification

Prix d'entrée$0.6 / 1M tokens
Prix de sortie$3.6 / 1M tokens
Prix mixte (3:1)$1.35 / 1M tokens

Vitesse

Tokens/sec52.8 tokens/s
Délai du premier token1.59s
Temps de réponse1.59s

Fournisseurs disponibles

(Unités internes LS)
FournisseurPrix d'entréePrix de sortie
Novita600K3.6M

Sources externes

LLM Stats