modelbenchmark.io

Doubao-Seed-Code

doubao-seed-code

Compare

Coding model for repository understanding, refactors, and agentic engineering tasks

Specification

most-agreed values

Context
256K
Max output
64K
Released
2025-11-11
Knowledge cutoff
2025-01-01
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.17
Output
$1.12
Cache read
$0.03

Quality

1 benchmark · 1 source

Composite
93rd
percentile of 334 scored models
Rank
25 / 334
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
coding92nd1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified78.8default · TRAESWE-bench

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

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
zenmux · volcengine$0.17$1.12$0.03256K64K