modelbenchmark.io

ByteDance-Seed/Seed-OSS-36B-Instruct

seed-oss-36b-instruct

Compare

Tool-capable chat model for instruction following and agentic application workflows

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-09-04
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.21
Output
$0.57

Quality

3 benchmarks · 1 source

Composite
65th
percentile of 334 scored models
Rank
118 / 334
±0.10 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning65th2/4 bench
math75th1/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
OTIS Mock AIME 2024-202567.5 ±6.3defaultEpoch AI2026-08-28
GPQA diamond71.5 ±2.7defaultEpoch AI2026-08-30
Chess Puzzles13.0 ±3.4defaultEpoch AI2026-08-28

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nvidia · bytedancefreefree262K262K
siliconflow · bytedance-seed$0.21$0.57262K262K
siliconflow-cn · bytedance-seed$0.21$0.57262K262K