ByteDance model product
Seed 1.8
8 is a large language model from ByteDance for multimodal agent scenarios.
Updated Oct 23, 2026. Default version: Seed 1.8
LLMBoard Score55.9Seed 1.8
Coverage60%56 benchmark families
Context window256KTokens
Official input priceN/AOfficial price unavailable
Seed 1.8 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Seed 1.8 Benchmark Results
Benchmark scores for Seed 1.8.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAMO Bench | Score60.00% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score81.30% | Rank01 | Participants15 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCountBench | Score96.30 points | Rank01 | Participants9 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLiveSports-3K | Score77.50% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkRefSpatialBench | Score56.30 points | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSimpleVQA | Score65.40 points | Rank01 | Participants17 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTempCompass | Score86.90% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkZEROBench | Score11.00 points | Rank01 | Participants15 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score92.30% | Rank02 | Participants103 | Percentile99.02% | EvidenceC | Evaluated |
| BenchmarkTOMATO | Score60.80% | Rank02 | Participants4 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkVideoMME w sub. | Score87.80% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkAetherCode | Score38.20% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkBeyond AIME | Score77.00% | Rank03 | Participants7 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBLINK | Score74.30% | Rank03 | Participants17 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkDUDE | Score69.40% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkEMMA | Score60.90% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score87.70% | Rank03 | Participants40 | Percentile94.87% | EvidenceC | Evaluated |
| BenchmarkMinerva | Score62.40% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMotionBench | Score70.60% | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkMuirBench | Score78.70% | Rank03 | Participants14 | Percentile84.62% | EvidenceC | Evaluated |
| BenchmarkOVBench | Score65.10% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkOVOBench | Score72.60% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkPHYBench | Score41.00% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkVideoSimpleQA | Score67.80% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkVLMsAreBiased | Score62.00% | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench Pro | Score1,930.00 points | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkLongVideoBench | Score77.40% | Rank04 | Participants6 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkMulti-SWE-Bench | Score42.00% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkTVBench | Score71.50% | Rank04 | Participants5 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkMMVU | Score73.10% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
Seed 1.8 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Seed 1.8 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.25 input, $2 output per 1M via Requesty
- Tracked offerings
- 1
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderRequesty | Provider model IDseed-1.8 | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context256K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Seed 1.8 Runtime Performance
Provider-specific output speed and catalog latency for Seed 1.8. 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 1.8 Specifications
Technical details for the model's default version.
- Version
- Seed 1.8
- Released
- Feb 17, 2026
- Knowledge cutoff
- Unknown
- Parameters
- N/A
- Context window
- 256K
- Max output
- 256K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Seed 1.8 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionSeed 1.8 | Released | LLMBoard55.90 | ParametersN/A | Context256K | Max output256K | Open weightsNo | LicenseProprietary |
Models similar to Seed 1.8
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
BY
Seed 2.0 Lite
ByteDance
BY
Seed 2.0 Mini
ByteDance
BY
Seed 2.0 Pro
ByteDance
BY
Seed 2.1 Turbo
ByteDance
BY
Seed 2.1 Pro
ByteDance
AC
Qwen3.5 27B
Alibaba Cloud / Qwen Team
What is Seed 1.8?
Key information about Seed 1.8 and its available data.
8 is a large language model optimized for multimodal agent scenarios. It includes enhanced agent capabilities, upgraded multimodal comprehension, and flexible context management.
Data as of 2026-10-22.
FAQ
Common questions about Seed 1.8.
When was Seed 1.8 released?
Seed 1.8's default version was released on Feb 17, 2026.
How much does Seed 1.8 cost?
No official standard PAYG price is currently available for Seed 1.8. The lowest tracked third-party offer starts at $0.25 input and $2 output via Requesty.
Who created Seed 1.8?
Seed 1.8 was created by ByteDance.
What is the context window for Seed 1.8?
The default version has a 256K token context window.
Is Seed 1.8 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Seed 1.8?
1 provider offerings are linked to the default version.