Skip to main content
AITier

Seed 2.1 Turbo

ByteDanceProprietary

Description

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.

Release Date
2026-06-24
Parameters
—
Context Length
—
Modalities
—

Capability Radar

80
general
50
coding
70
reasoning
51
scienceest.
70
agents
70
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability51
57.0
LS
Multimodal Ranking76
66.0
LS
Reasoning73
57.0
LS

Benchmark Scores (LLM Stats)

3d

BLINK79.4%SR

Agents

BrowseComp84.9%SR
GDPval82.7%SR
MCP Atlas80.3%SR
OSWorld76.4%SR
Web Bench73.6%SR
OfficeQA Pro71.1%SR
MobileWorld70.0%SR
Terminal-Bench 2.167.6%SR
CyberGym67.0%SR
OneMillion Bench66.6%SR
SeedClawBench63.8%SR
WildClawBench62.8%SR
Trae Code Gen59.7%SR
SWE-Bench Pro57.0%SR
Trae Error Fix56.7%SR
xDailyBench56.4%SR
Finance Agent v1.156.0%SR
Workspace Bench54.7%SR
Agent Startup Bench54.0%SR
Program Bench49.4%SR
Toolathlon49.1%SR
Doubao Multi-Turn Bench49.0%SR
PresentBench48.3%SR
Repo Env46.7%SR
ClawEval-MM46.0%SR
NL2Repo43.7%SR
CreativeWork34.5%SR
SWE-Atlas30.6%SR
APEX-Agents29.2%SR
GameWorld25.9%SR
DeepSWE23.0%SR
PostTrainBench18.3%SR

Biology

SciCode57.8%SR

Chemistry

SuperGPQA67.4%SR
SuperChem56.6%SR

Code

FrontierCS50.8%SR
Artifacts Bench47.0%SR

Coding

AetherCode67.9%SR
Image2FloorPlan35.9%SR

Embodied

EmbSpatialBench0.82 / 100SR

General

MMMU-Pro82.2%SR
SimpleVQA0.71 / 100SR
KINA46.6%SR
MSQA42.0%SR

Image To Text

OCRBench_V262.8%SR

Knowledge

VideoSimpleQA71.4%SR
WorldBench63.7%SR

Long Context

DUDE83.1%SR
LongVideoBench80.6%SR
MMLongBench-128K76.9%SR
LVBench76.8%SR

Math

MathVision92.7%SR
MathVista90.5%SR
MathVerse89.2%SR
Beyond AIME88.0%SR
EMMA78.4%SR
FrontierScience Olympiad76.0%SR
DynaMath68.1%SR
Humanity's Last Exam54.6%SR
MathArena Apex35.4%SR
LiveMathematicianBench27.7%SR
HorizonMath2.0%SR

Multimodal

CharXiv-D94.6%SR
Video-MME89.0%SR
CharXiv-R83.6%SR
OVOBench79.2%SR
TVBench77.2%SR
LiveSports-3K77.1%SR
MotionBench74.8%SR
TreeBench71.1%SR
ChartQAPro70.9%SR
OVBench69.7%SR
VLMsAreBiased68.3%SR
VideoHolmes67.6%SR
Minerva65.9%SR
CrossVid63.2%SR
BabyVision62.9%SR
ContPhy61.1%SR
MeasureBench58.9%SR
ZEROBench0.57 / 100SR
TOMATO56.8%SR
VisuLogic0.53 / 100SR
WorldVQA48.6%SR
VisFactor43.9%SR
MMSIBench31.4%SR

Reasoning

ERQA71.3%SR
ArcAGI261.3%SR
FrontierScience Research33.3%SR

Spatial Reasoning

RealWorldQA86.3%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

Structured Output
90
Legal
80
Long Context
80
Search
80
Spatial Reasoning
80
Embodied
80
Finance
80
General
80
3d
80
Image To Text
70
Math
70
Multimodal
70
Safety
70
Healthcare
70
Economics
70
Tool Calling
70
Video
70
Vision
70
Physics
60
Reasoning
60
Agents
60
Biology
60
Chemistry
60
Frontend Development
50
Code
50
Coding
50
Science
30
Systems
20

Pricing

No pricing data available

Speed

No speed data available

Provider Price Ranking

No provider data available

External Sources

LLM StatsArtificial Analysis