Doubao Seed-2.1-pro-0915 hands-on: tool-calling score jumps 38.4% to 64.8%, coding cost down 40%
vista8 · x · 2026-09-17
The author tests ByteDance's continuously-updated Doubao-Seed-Evolving model (stabilized as Seed-2.1-pro-0915) across 7 real tasks.
- Official numbers: complex repo understanding +12.4%, tool-calling benchmark score jumped from 38.4% to 64.8%, overall coding cost down over 40%
- Integrated into Doubao Work and TRAE, API live on Volcano Ark; strengthened multimodal coding and agentic capabilities
- Test cases include deep research (auto-planned a scoring framework, scraped 100+ Obsidian AI plugins from the marketplace and GitHub, wrote results to Feishu), Mac app development, Blender 3D modeling, video generation, and a fishing-spot map
The author leaves the quality judgment to readers.
More from coding & agent
- Live viral-post analyzer built with Jev: structured outputs enable 0.5s real-time analysis — jasonkneen · 2026-09-17
- OpenEnv to add multi-harness RL training across Claude Code, Codex, Gemini CLI and more — SergioPaniego · 2026-09-17
- One Prompt, 100 Parallel Agents: How Google's Agent Graphs Coordinates Multi-Agent Work — goyalshaliniuk · 2026-09-17
- Devs hail jev as a missing primitive: compose AI into systems, not as the system — teropa · 2026-09-17
- Dev builds model router with Jev to auto-route requests to the best-fit LLM — emeka_boris · 2026-09-17
- Real-time transcription: how to recover state when the WebSocket drops mid-sentence — tresch_24 · 2026-09-17