Seed 2.0 Mini
ByteDanceProprietary
Descripción
Built for low-latency, high-concurrency, cost-sensitive use cases, with flexible deployment, four-tier thinking, and multimodal
Fecha de lanzamiento
2026-02-17
Parámetros
—
Longitud del contexto
262K
Modalidades
image, text, video
Radar de capacidades
21
general
10
coding
100
reasoning
68
scienceest.
10
agents
70
multimodal
Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking multimodal | 124 | 34.0 | LS |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Chat
Multi-Challenge
61.1%Aut.
Chemistry
SuperChem
16.2%Aut.
Code
CL-bench
14.8%Aut.
Coding
AetherCode
29.8%Aut.
Factuality
SimpleQA Verified
18.9%Aut.
General
LongFact Concepts
91.4%Aut.
LongFact Objects
87.0%Aut.
Healthcare
HealthBench
30.0%Aut.
HealthBench Hard
15.3%Aut.
Language
COLLIE
91.2%Aut.
MMLU-Pro
83.6%Aut.
MMMLU
81.6%Aut.
Long Context
MRCR v2 (8-needle)
51.4%Aut.
Math
CodeForces
1644.00 / 3000Aut.
AIME 2025
87.0%Aut.
AIME 2026
86.7%Aut.
MathVista-Mini
85.5%Aut.
MathVision
78.1%Aut.
Beyond AIME
69.0%Aut.
DynaMath
58.9%Aut.
MathArena Apex
4.2%Aut.
Multimodal
VideoMMMU
80.6%Aut.
MMMU
79.7%Aut.
Physics
PHYBench
56.0%Aut.
Reasoning
Graphwalks parents <128k
93.0%Aut.
CharXiv-D
91.9%Aut.
Global PIQA
89.2%Aut.
FRAMES
80.5%Aut.
GPQANYU + Cohere + Anthropic (2023)
79.0%Aut.
CharXiv-R
70.8%Aut.
LiveCodeBench v6
64.1%Aut.
Graphwalks BFS <128k
64.1%Aut.
SuperGPQA
61.6%Aut.
FActScoreMin et al. (NYU/UW, 2023)
50.4%Aut.
FrontierScience Olympiad
44.0%Aut.
ARC-AGI
29.8%Aut.
Humanity's Last Exam (no tools, text-only)
13.3%Aut.
FrontierScience Research
3.3%Aut.
ArcAGI2
2.3%Aut.
ARC-AGI v2
1.5%Aut.
Video
LiveSports-3K
73.3%Aut.
OVOBench
70.4%Aut.
VideoSimpleQA
67.7%Aut.
OVBench
60.1%Aut.
VideoHolmes
58.6%Aut.
CrossVid
58.6%Aut.
ContPhy
55.9%Aut.
Minerva
54.7%Aut.
TOMATO
47.4%Aut.
Vision
CountBench
0.95 / 100Aut.
VLMsAreBlind
93.1%Aut.
TempCompass
83.7%Aut.
RealWorldQA
81.6%Aut.
VideoMME w sub.
81.2%Aut.
MMStar
79.1%Aut.
MuirBench
78.0%Aut.
LongVideoBench
74.8%Aut.
BLINK
73.4%Aut.
MMMU-Pro
71.4%Aut.
TVBench
70.5%Aut.
MMVU
69.0%Aut.
DUDE
68.9%Aut.
SimpleVQA
0.69 / 100Aut.
LVBench
66.6%Aut.
ChartQAPro
65.2%Aut.
Hallusion Bench
65.1%Aut.
MotionBench
64.4%Aut.
OCRBench_V2
58.5%Aut.
VLMsAreBiased
58.4%Aut.
TreeBench
57.3%Aut.
EMMA
57.0%Aut.
ERQA
56.3%Aut.
HiPhO
55.8%Aut.
RefSpatialBench
0.56 / 100Aut.
MTVQA
50.6%Aut.
MMLongBench-Doc
0.49 / 100Aut.
WorldVQA
47.6%Aut.
VisuLogic
0.40 / 100Aut.
BabyVision
38.7%Aut.
ZEROBench-Sub
0.36 / 100Aut.
VisFactor
23.6%Aut.
OmniDocBench 1.5
11.0%Aut.
ZEROBench
0.07 / 100Aut.
Índices de evaluación AA
(Artificial Analysis)No hay datos de evaluación AA disponibles
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Math100
Reasoning28
General21
Language90
Writing90
Search80
Biology80
Legal70
Physics70
Finance70
3d70
Chat60
Image To Text60
Long Context60
Multimodal60
Spatial Reasoning60
Grounding60
Healthcare60
Communication60
Economics60
Video60
Vision60
Structured Output50
Chemistry50
Knowledge40
Science30
Coding30
Factuality20
Agents10
Code10
Precios
Precio de entrada$0 / 1M tokens
Precio de salida$0 / 1M tokens
Precio mixto (3:1)$0 / 1M tokens
Velocidad
No hay datos de velocidad disponibles
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
5 proveedores
Más barato: ByteDanceMás caro: Requesty
ProveedorEntradaSalida
1ByteDancePRINCIPAL
$0
$0
2DeepInfra
$0
$0
3OpenRouter
$0.1
$0.4
4Kilo Gateway
$0.1
$0.4
5Requesty
$0.1
$0.4
Comparar precios entre diferentes proveedores de API para este modelo.