Перейти к основному содержанию
AITier

Seed 2.1 Turbo

ByteDanceProprietary

Описание

ByteDance's low-cost, low-latency next-generation agent model for large-scale production. A deep-thinking model with the full feature set of Seed 2.1 Pro and comparable performance, it is designed for enterprise-grade deployments handling high volumes of online calls across coding, long-chain agents, and multimodal tasks. Served via Volcano Engine as Doubao-Seed-2.1-turbo.

Дата выхода
2026-06-24
Параметры
—
Длина контекста
262K
Модальности
image, text, video

Радар способностей

60
general
50
coding
60
reasoning
51
scienceоцен.
70
agents
70
multimodal

При отсутствии специализированных научных бенчмарков Science оценивается по научным категориям LLM Stats или на основе рассуждений.

Рейтинги

Домен#МестоОценкаИсточник
Агентные возможности48
49.0
LS
Мультимодальный рейтинг15
65.0
LS

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Agents

Web Bench73.6%Сам.
OfficeQA Pro71.1%Сам.
MobileWorld70.0%Сам.
OneMillion Bench66.6%Сам.
SeedClawBench63.8%Сам.
WildClawBench62.8%Сам.
xDailyBench56.4%Сам.
Finance Agent v1.156.0%Сам.
Workspace Bench54.7%Сам.
Agent Startup Bench54.0%Сам.
Program Bench49.4%Сам.
Toolathlon49.1%Сам.
Doubao Multi-Turn Bench49.0%Сам.
PresentBench48.3%Сам.
ClawEval-MM46.0%Сам.
CreativeWork34.5%Сам.
SWE-Atlas30.6%Сам.
GameWorld25.9%Сам.
PostTrainBench18.3%Сам.

Chemistry

SuperChem56.6%Сам.

Code

CyberGym67.0%Сам.
Artifacts Bench47.0%Сам.
NL2Repo43.7%Сам.
DeepSWE23.0%Сам.

Coding

AetherCode67.9%Сам.
Trae Code Gen59.7%Сам.
Trae Error Fix56.7%Сам.
Repo Env46.7%Сам.

General

GDPval82.7%Сам.

Knowledge

KINA46.6%Сам.
MSQA42.0%Сам.

Math

MathVision92.7%Сам.
MathVista90.5%Сам.
MathVerse89.2%Сам.
Beyond AIME88.0%Сам.
DynaMath68.1%Сам.
MathArena Apex35.4%Сам.
LiveMathematicianBench27.7%Сам.
HorizonMath2.0%Сам.

Multimodal

Video-MME89.0%Сам.
OSWorld76.4%Сам.

Reasoning

CharXiv-D94.6%Сам.
BrowseCompOpenAI (2025)84.9%Сам.
CharXiv-R83.6%Сам.
MCP Atlas80.3%Сам.
FrontierScience Olympiad76.0%Сам.
Terminal-Bench 2.167.6%Сам.
SuperGPQA67.4%Сам.
ArcAGI261.3%Сам.
SciCode57.8%Сам.
SWE-Bench ProPrinceton NLP (2024)57.0%Сам.
Humanity's Last Exam54.6%Сам.
FrontierCS50.8%Сам.
FrontierScience Research33.3%Сам.
APEX-Agents29.2%Сам.

Video

OVOBench79.2%Сам.
LiveSports-3K77.1%Сам.
VideoSimpleQA71.4%Сам.
OVBench69.7%Сам.
VideoHolmes67.6%Сам.
Minerva65.9%Сам.
CrossVid63.2%Сам.
ContPhy61.1%Сам.
TOMATO56.8%Сам.

Vision

RealWorldQA86.3%Сам.
DUDE83.1%Сам.
EmbSpatialBench0.82 / 100Сам.
MMMU-Pro82.2%Сам.
LongVideoBench80.6%Сам.
BLINK79.4%Сам.
EMMA78.4%Сам.
TVBench77.2%Сам.
MMLongBench-128K76.9%Сам.
LVBench76.8%Сам.
MotionBench74.8%Сам.
ERQA71.3%Сам.
TreeBench71.1%Сам.
SimpleVQA0.71 / 100Сам.
ChartQAPro70.9%Сам.
VLMsAreBiased68.3%Сам.
WorldBench63.7%Сам.
BabyVision62.9%Сам.
OCRBench_V262.8%Сам.
MeasureBench58.9%Сам.
VisuLogic0.53 / 100Сам.
WorldVQA48.6%Сам.
VisFactor43.9%Сам.
Image2FloorPlan35.9%Сам.
MMSIBench31.4%Сам.
ZEROBench0.11 / 100Сам.

Индексы оценки AA

(Artificial Analysis)

Нет данных AA оценки

Оценки категорий LLM Stats

(LLM Stats (zeroeval))
Structured Output
90
Legal
80
Long Context
80
Search
80
Spatial Reasoning
80
Embodied
80
3d
80
Image To Text
70
Multimodal
70
Safety
70
Finance
70
Healthcare
70
Coding
70
Economics
70
Tool Calling
70
Video
70
Vision
70
Knowledge
60
Math
60
Physics
60
Reasoning
60
General
60
Agents
60
Biology
60
Chemistry
60
Science
50
Frontend Development
50
Code
50
Systems
20

Цены

Цена ввода$0.5 / 1M токенов
Цена вывода$2.5 / 1M токенов
Смешанная цена (3:1)$1 / 1M токенов

Скорость

Нет данных о скорости

Рейтинг цен провайдеров

Рейтинг цен провайдеров

4 провайдеров

Самый дешевый: ByteDanceСамый дорогой: Kilo Gateway
ПровайдерВводВывод
1ByteDanceОсновной
$0.5
$2.5
2NanoGPT
$0.5
$2.5
3OpenRouter
$0.5
$2.5
4Kilo Gateway
$0.5
$2.5

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки

LLM StatsArtificial Analysis