llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

ByteDance model product

Seed 2.0 Pro

0 Pro is a general-purpose agent model from ByteDance for long-chain reasoning, complex workflows, multimodal understanding, instruction following, and coding.

Updated Oct 23, 2026. Default version: Seed 2.0 Pro

LLMBoard Score67.8Seed 2.0 Pro
Coverage0%6 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Seed 2.0 Pro Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Seed 2.0 Pro LLMBoard score breakdown

Seed 2.0 Pro Benchmark Results

Benchmark scores for Seed 2.0 Pro.

11 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkLiveCodeBench v6Score87.80%Rank10Participants67Percentile86.36%EvidenceCEvaluatedOct 22, 2026
BenchmarkAIME 2026Score94.20%Rank12Participants27Percentile57.69%EvidenceCEvaluatedOct 22, 2026
BenchmarkAIME 2025Score98.30%Rank13Participants122Percentile90.08%EvidenceCEvaluatedOct 22, 2026
BenchmarkBrowseCompScore77.30%Rank27Participants70Percentile62.32%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena VisionScore1,274.42 ratingRank31Participants113Percentile73.21%EvidenceAEvaluatedOct 19, 2026
BenchmarkSWE-Bench VerifiedScore76.50%Rank33Participants120Percentile73.11%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena Vision Style ControlScore1,256.47 ratingRank37Participants113Percentile67.86%EvidenceAEvaluatedOct 19, 2026
BenchmarkGPQAScore88.90%Rank39Participants256Percentile85.10%EvidenceCEvaluatedOct 22, 2026
BenchmarkLM Arena TextScore1,448.19 ratingRank42Participants218Percentile81.11%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena Text Style ControlScore1,456.31 ratingRank47Participants218Percentile78.80%EvidenceAEvaluatedOct 20, 2026
BenchmarkLM Arena Text FactualityScore1,419.72 ratingRank99Participants131Percentile24.62%EvidenceAEvaluatedOct 20, 2026

Seed 2.0 Pro Arena Results

Preference and agent-evaluation results for the default version.

30 of 100 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenatextCategorypolishRank14Rating / score1,487.52Votes1,646ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategorypolishRank15Rating / score1,487.31Votes1,646ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryenglishRank17Rating / score1,293.64Votes4,042ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategorypolishRank18Rating / score1,439.70Votes1,104ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategoryenglishRank20Rating / score1,277.52Votes4,042ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategoryindustry medicine and healthcareRank23Rating / score1,490.13Votes5,833ObservationsN/AResult dateOct 20, 2026
ArenavisionCategorychineseRank23Rating / score1,337.34Votes869ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategorychineseRank24Rating / score1,313.84Votes869ObservationsN/AResult dateOct 19, 2026
Arenatext factualityCategorykoreanRank25Rating / score1,406.64Votes835ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryspanishRank27Rating / score1,470.42Votes2,563ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryhumorRank27Rating / score1,275.12Votes393ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryindustry medicine and healthcareRank28Rating / score1,470.27Votes5,833ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategoryhumorRank29Rating / score1,257.08Votes393ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryoverallRank31Rating / score1,274.42Votes10,972ObservationsN/AResult dateOct 19, 2026
ArenavisionCategorydiagramRank32Rating / score1,289.39Votes2,846ObservationsN/AResult dateOct 19, 2026
ArenavisionCategoryocrRank32Rating / score1,283.77Votes7,715ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryspanishRank33Rating / score1,461.56Votes2,563ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryfrenchRank33Rating / score1,489.72Votes2,579ObservationsN/AResult dateOct 20, 2026
Arenatext factualityCategoryjapaneseRank34Rating / score1,389.61Votes552ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategorydiagramRank35Rating / score1,287.41Votes2,846ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryfrenchRank36Rating / score1,471.29Votes2,579ObservationsN/AResult dateOct 20, 2026
ArenatextCategorynon englishRank36Rating / score1,441.44Votes43,883ObservationsN/AResult dateOct 20, 2026
ArenavisionCategorycreative writing visionRank36Rating / score1,258.36Votes543ObservationsN/AResult dateOct 19, 2026
Arenavision style controlCategoryocrRank36Rating / score1,270.36Votes7,715ObservationsN/AResult dateOct 19, 2026
Arenatext style controlCategorycodingRank37Rating / score1,513.65Votes22,067ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry software and it servicesRank37Rating / score1,502.27Votes30,992ObservationsN/AResult dateOct 20, 2026
Arenavision style controlCategoryoverallRank37Rating / score1,256.47Votes10,972ObservationsN/AResult dateOct 19, 2026
ArenatextCategoryindustry software and it servicesRank39Rating / score1,474.25Votes30,992ObservationsN/AResult dateOct 20, 2026
Arenatext style controlCategoryindustry business and management and financial operationsRank39Rating / score1,463.97Votes15,503ObservationsN/AResult dateOct 20, 2026
ArenavisionCategoryhomeworkRank39Rating / score1,283.70Votes1,842ObservationsN/AResult dateOct 19, 2026

Seed 2.0 Pro Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.475 input, $2.37 output per 1M via Volcengine Ark
Tracked offerings
6
6 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderVolcengine ArkProvider model IDdoubao-seed-2-0-pro-260215RegionglobalInput / 1M$0.475Output / 1M$2.37Context256KUpdatedOct 23, 2026
ProviderDeep InfraProvider model IDByteDance/Seed-2.0-proRegionglobalInput / 1M$0.50Output / 1M$3Context256KUpdatedOct 23, 2026
ProviderMerge GatewayProvider model IDbytedance/dola-seed-2.0-proRegionglobalInput / 1M$0.50Output / 1M$3Context131.1KUpdatedOct 23, 2026
ProviderRequestyProvider model IDseed-2.0-proRegionglobalInput / 1M$0.50Output / 1M$3Context256KUpdatedOct 23, 2026
ProviderEmpirioLabs AIProvider model IDseed-2-0-proRegionglobalInput / 1M$0.63Output / 1M$3.79Context256KUpdatedOct 23, 2026
ProviderOfoxProvider model IDvolcengine/doubao-seed-2.0-proRegionglobalInput / 1M$0.67Output / 1M$3.36Context256KUpdatedOct 23, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Seed 2.0 Pro Runtime Performance

Provider-specific output speed and catalog latency for Seed 2.0 Pro. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Seed 2.0 Pro Specifications

Technical details for the model's default version.

Version
Seed 2.0 Pro
Released
Feb 14, 2026
Knowledge cutoff
Jan 1, 2024
Parameters
N/A
Context window
256K
Max output
131.1K
Inputs
image, text, video
Outputs
text
Open weights
No
License
Proprietary

Seed 2.0 Pro Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionSeed 2.0 ProReleasedFeb 14, 2026LLMBoard67.79ParametersN/AContext256KMax output131.1KOpen weightsNoLicenseProprietary

Models similar to Seed 2.0 Pro

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#67+2.65
BY

Seed 2.1 Turbo

ByteDance

70.44 LLMBoard

Details
#41+7.82
BY

Seed 2.1 Pro

ByteDance

75.61 LLMBoard

Details
#110-11.89
BY

Seed 1.8

ByteDance

55.90 LLMBoard

Details
#123-15.92
BY

Seed 2.0 Lite

ByteDance

51.87 LLMBoard

Details
#150-21.99
BY

Seed 2.0 Mini

ByteDance

45.80 LLMBoard

Details
#71+0.21
OP

GPT-5.2

OpenAI

68.00 LLMBoard

Details

What is Seed 2.0 Pro?

Key information about Seed 2.0 Pro and its available data.

0 Pro is ByteDance's general-purpose agent model with multimodal understanding across text, image, and video. It is designed for long-chain reasoning, complex workflows, instruction following, and coding.

Data as of 2026-10-22.

FAQ

Common questions about Seed 2.0 Pro.

When was Seed 2.0 Pro released?

Seed 2.0 Pro's default version was released on Feb 14, 2026.

How much does Seed 2.0 Pro cost?

No official standard PAYG price is currently available for Seed 2.0 Pro. The lowest tracked third-party offer starts at $0.475 input and $2.37 output via Volcengine Ark.

Who created Seed 2.0 Pro?

Seed 2.0 Pro was created by ByteDance.

What is the context window for Seed 2.0 Pro?

The default version has a 256K token context window.

Is Seed 2.0 Pro open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Seed 2.0 Pro?

6 provider offerings are linked to the default version.

Browse runtime rankings