Seed-OSS-36B-Instruct
ByteDance SeedProprietary
Description
ByteDance's flagship general-purpose agent model focused on long-chain reasoning and robustness in complex workflows. Features comprehensive multimodal understanding (text, image, video), enhanced instruction-following, and strong coding capabilities. Competes with GPT-5.2 and Gemini 3 Pro across scientific, reasoning, and coding benchmarks.
Release Date
2025-08-20
Parameters
—
Context Length
—
Modalities
image, text, video
Capability Radar
33
general
77
coding
83
reasoning
53
science
80
agents
90
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 277 | 54.0 | AA |
| General Ranking | 303 | 43.0 | AA |
| Science | 326 | 44.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Math
AIME 2025
98.3%SR
AIME 2026
94.2%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
88.9%SR
LiveCodeBench v6
87.8%SR
BrowseCompOpenAI (2025)
77.3%SR
SWE-Bench Verified
76.5%SR
AA Evaluation Indices
(Artificial Analysis)Math Index(Artificial Analysis)84.7
Aime 25(MAA (Mathematical Association of America))84.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))81.5
Livecodebench(UC Berkeley + MIT + Cornell (2024))76.5
Gpqa(NYU + Cohere + Anthropic (2023))72.6
Lcr(Artificial Analysis)61.3
Tau2(Sierra + U Toronto + Vector Institute (2025))49.4
Ifbench(Google Research (2023))41.9
Intelligence Index(Artificial Analysis)12.1
Hle(Center for AI Safety + Scale AI (2025))9.9
Terminalbench Hard(Stanford × Laude Institute (2026))6.8
LLM Stats Category Scores
(LLM Stats (zeroeval))Math100
Physics90
Reasoning90
General90
Biology90
Chemistry90
Search80
Frontend Development80
Agents80
Code80
Pricing
Input Price$0.21 / 1M tokens
Output Price$0.57 / 1M tokens
Blended Price (3:1)$0.3 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
2 providers
Cheapest: DeepInfraMost Expensive: ByteDance Seed
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2ByteDance SeedPRIMARY
$0.21
$0.57
Compare pricing across different API providers for this model.