Skip to main content
AITier

Seed 1.8

ByteDanceProprietary

Description

Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.

Release Date
2026-02-17
Parameters
—
Context Length
—
Modalities
image, text, video

Capability Radar

39
general
100
coding
70
reasoning
51
scienceest.
50
agents
70
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

Domain#RankScoreSource
Agentic Capability85
37.0
LS
Multimodal Ranking91
48.0
LS

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

AndroidWorld70.7%SR

Chat

Multi-Challenge66.7%SR

Coding

AetherCode38.2%SR

General

MMLU92.3%SR

Language

MMLU-Pro84.9%SR

Math

AIME 202594.3%SR
MathVista87.7%SR
MathVision81.3%SR
Beyond AIME77.0%SR
DynaMath61.5%SR
AMO Bench60.0%SR

Multimodal

MMMU83.4%SR
VideoMMMU82.7%SR
OSWorld61.9%SR

Physics

PHYBench41.0%SR

Reasoning

LiveCodeBench Pro1930.00 / 3000SR
BrowseComp-zh81.3%SR
LiveCodeBench v679.5%SR
SWE-Bench Verified72.9%SR
CharXiv-R71.4%SR
ARC-AGI67.9%SR
BrowseCompOpenAI (2025)67.6%SR
SuperGPQA64.8%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)45.2%SR
Multi-SWE-Bench42.0%SR
Humanity's Last Exam (with tools, text-only)40.9%SR

Search

WideSearch63.8%SR

Tool Calling

BFCL-V457.2%SR

Video

LiveSports-3K77.5%SR
OVOBench72.6%SR
VideoSimpleQA67.8%SR
OVBench65.1%SR
Minerva62.4%SR
TOMATO60.8%SR

Vision

CountBench96.30 / 100SR
SimpleVQA65.40 / 100SR
RefSpatialBench56.30 / 100SR
ZEROBench11.00 / 100SR
VLMsAreBlind93.0%SR
AI2D89.1%SR
VideoMME w sub.87.8%SR
TempCompass86.9%SR
MMStar79.9%SR
MuirBench78.7%SR
LongVideoBench77.4%SR
BLINK74.3%SR
MMMU-Pro73.2%SR
MMVU73.1%SR
LVBench73.0%SR
TVBench71.5%SR
MotionBench70.6%SR
DUDE69.4%SR
Hallusion Bench63.9%SR
VLMsAreBiased62.0%SR
EMMA60.9%SR
ERQA58.8%SR
OmniDocBench 1.510.6%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Code
100
Image To Text
65
Grounding
56
Reasoning
53
General
39
Spatial Reasoning
31
Vision
7
Multimodal
3
Language
90
Legal
80
Finance
80
Healthcare
80
Chat
70
Knowledge
70
Long Context
70
Math
70
Search
70
Frontend Development
70
3d
70
Communication
70
Video
70
Agents
60
Chemistry
60
Economics
60
Physics
50
Tool Calling
50
Science
40
Coding
40
Structured Output
10

Pricing

Input Price$0 / 1M tokens
Output Price$0 / 1M tokens
Blended Price (3:1)$0 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

3 providers

Cheapest: ByteDanceMost Expensive: Requesty
ProviderInputOutput
1ByteDancePRIMARY
$0
$0
2DeepInfra
$0
$0
3Requesty
$0.25
$2

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis