Qwen2.5-Omni-7B
Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK
Description
Qwen2.5-Omni is the flagship end-to-end multimodal model in the Qwen series. It processes diverse inputs including text, images, audio, and video, delivering real-time streaming responses through text generation and natural speech synthesis using a novel Thinker-Talker architecture.
Date de sortie
2025-03-27
Paramètres
7.0B
Longueur du contexte
—
Modalités
—
Radar de capacités
50
general
80
coding
60
reasoning
26
scienceest.
0
agents
90
multimodal
Science utilise un proxy de raisonnement lorsque les benchmarks scientifiques dédiés ne sont pas disponibles.
Classements
| Domaine | #Rang | Score | Source |
|---|---|---|---|
| Multimodal Ranking | 52 | 74.0 | LS |
Scores de benchmarks (LLM Stats)
Audio
VocalSound
93.9%Aut.
GiantSteps Tempo
88.0%Aut.
MMAU Music
69.2%Aut.
MMAU Sound
67.9%Aut.
MMAU
65.6%Aut.
MMAU Speech
59.8%Aut.
OmniBench Music
52.8%Aut.
CoVoST2 en-zh
0.41 / 100Aut.
MusicCaps
32.8%Aut.
Common Voice 15
0.08 / 100Aut.
Biology
GPQA
30.8%Aut.
Code
HumanEval
78.7%Aut.
Communication
VoiceBench Avg
74.1%Aut.
MM-MT-Bench
0.06 / 100Aut.
Creativity
Meld
57.0%Aut.
Finance
MMLU-Pro
47.0%Aut.
General
MBPP
0.73 / 100Aut.
MMLU-Redux
71.0%Aut.
MultiPL-E
65.8%Aut.
MMStar
64.0%Aut.
MME-RealWorld
61.6%Aut.
MMMU
59.2%Aut.
MMMU-Pro
36.6%Aut.
LiveBench
29.6%Aut.
NMOS
0.05 / 100Aut.
Grounding
PointGrounding
66.5%Aut.
Healthcare
CRPErelation
76.5%Aut.
Image To Text
DocVQA
95.2%Aut.
TextVQA
84.4%Aut.
OCRBench_V2
57.8%Aut.
Language
FLEURS
0.04 / 100Aut.
Long Context
EgoSchema
68.6%Aut.
Math
GSM8k
88.7%Aut.
MATH
71.5%Aut.
MathVista
67.9%Aut.
MathVision
25.0%Aut.
Multimodal
ChartQA
85.3%Aut.
AI2D
83.2%Aut.
MMBench-V1.1
81.8%Aut.
VideoMME w sub.
72.4%Aut.
MVBench
70.3%Aut.
MuirBench
59.2%Aut.
OmniBench
56.1%Aut.
Spatial Reasoning
RealWorldQA
70.3%Aut.
Vision
ODinW
42.4%Aut.
Indices d'évaluation AA
Aucune donnée d'évaluation AA disponible
Scores par catégorie LLM Stats
Image To Text90
Code80
Spatial Reasoning70
Video70
Vision70
Long Context70
Math60
Multimodal60
Reasoning60
Finance50
General50
Healthcare50
Language50
Legal50
Biology30
Chemistry30
Physics30
Communication10
Speech To Text0
Tarification
Aucune donnée de prix disponible
Vitesse
Aucune donnée de vitesse disponible
Fournisseurs disponibles
(Unités internes LS)Aucune donnée de fournisseur disponible