Model

Seed-OSS-36B

OPEN

ByteDance · Seed family · released Aug 20, 2025

Apache-2.0 open release with native 512K context and a tunable thinking-length budget; trained on only 12T tokens.

ReasoningCodingVisionFunction callingTool useAgentic

1572.9

Elo · rank #107

Parameters

36B

Active params

36B (dense)

Context

512K tokens

Architecture

Dense Transformer (RoPE, GQA, RMSNorm, SwiGLU)

License

Apache-2.0

Languages

—

API price (in/out)

No hosted API

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

AIMEMath91.7%#39

best: GPT-5.2 · 100.0%

ARC-AGI-2Reasoning1.4%#26

best: GPT-5.6 · 92.5%

GPQA DiamondReasoning71.4%#118

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning10.1%#90

best: Claude Sonnet 5 · 57.4%

IFEvalReasoning85.8%#53

best: Gemma 4 26B A4B · 98.5%

LiveCodeBenchCoding67.4%#76

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMLU-ProKnowledge82.7%#43

best: Claude Fable 5 · 91.5%

MMLUKnowledge87.4%#34

best: OpenAI o3 · 92.9%

MMMLUKnowledge78.4%#31

best: Gemini 3.1 Pro · 92.6%

SimpleQAKnowledge9.7%#38

best: GPT-4.5 · 62.5%

SuperGPQAReasoning55.7%#17

best: Qwen3.7-Max · 73.6%

SWE-bench VerifiedCoding56.0%#85

best: Claude Fable 5 · 95.0%

tau-benchAgents70.4%#6

best: Claude Opus 4.1 · 82.4%

Run it locally

VRAM @ Q4

21.8 GB

VRAM @ FP16

72 GB

Fits on (Q4)

RTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB

Throughput data unavailable.

Quantizations

GGUF Q4 · GGUF Q8

Seed family

Elo progression across releases

Seed1.5-ThinkingApr 20251595.3 Seed-OSS-36BAug 20251572.9

Resources

HFByteDance-Seed/Seed-OSS-36B-Instruct GHByteDance-Seed/seed-oss

API price weights · each benchmark row carries its own source badge (see methodology)