Skip to content
ByteDance

Doubao Seed 2.0 Code

coding

ByteDanceReleased on 2026-02-14

ByteDance's coding-specialized model, deeply optimized for Agentic Programming. Delivers exceptional performance on Terminal Bench, SWE-Bench-Verified-Openhands, and Multi-SWE-Bench-Flash-Openhands. Native 256K context, first Chinese model with visual understanding for code. Compatible with Anthropic API, optimized for TRAE, Cursor, Cline, and Codex CLI.

79
Overall Score

Core Specs

256K
Context Window
128K
Max Output
Reasoning
Open Source
Multimodal Support
textvision

User Feedback Highlights

Based on community feedback. Hover to see original reviews.

+ Native 256K context for large codebases+ Codeforces 3020 (gold medalist level)+ Deeply optimized for Agentic Programming Limited to Volcengine access outside China+ Anthropic API compatible+ Optimized for TRAE, Cursor, Cline ecosystems Same pricing as Pro (no cost advantage) Terminal Bench lower than GPT-5.2 (55.8 vs 62.4) English code comments may be less natural Still trails Claude Opus 4.5 on SWE-Bench (76.5 vs 80.9)+ First Chinese coding model with vision
Sentiment:👍 70%😐 22%👎 8%

Pros & Cons

Pros

  • +Deeply optimized for Agentic Programming
  • +Codeforces 3020 (gold medalist level)
  • +Native 256K context for large codebases
  • +First Chinese coding model with vision
  • +Anthropic API compatible
  • +Optimized for TRAE, Cursor, Cline ecosystems

Cons

  • Still trails Claude Opus 4.5 on SWE-Bench (76.5 vs 80.9)
  • Terminal Bench lower than GPT-5.2 (55.8 vs 62.4)
  • Same pricing as Pro (no cost advantage)
  • English code comments may be less natural
  • Limited to Volcengine access outside China

Pricing

Input (per 1M tokens)$0.47
Output (per 1M tokens)$2.37
Free trial available
Updated on 2026-03-26

Get Started

1Visit the provider's website
2Create an account
3Start using the model

Benchmarks

userRating8.4%
codeforces3020%
sweBenchVerified76.5%
terminalBench55.8%
liveCodeBenchV687.8%