GLM 5.3 Flash takes 54% of Bolt Forge prompts in three days, beating DeepSeek and Kimi combined
SimplyAnnisa · x · 2026-09-18
Bolt open-sourced its Forge model mode to 11M+ users, and the early usage split is striking: GLM 5.3 Flash captured 54% of prompts in three days, more than DeepSeek V4 Pro (17%), GLM 5.3 (15%), and Kimi K3 (14%) combined. The fastest, cheapest model with up to 2x prompt size won, showing builders prioritize speed and cost over model hype in coding workflows.
Related event: Bolt Data Shows GLM 5.3 Flash Leads Open Models at 54% Usage(6 posts)→
More from coding & agent
- awa-video-reel: free Claude Code skill auto-edits shorts and records website B-roll — TawohAwa · 2026-11-02
- Econ PhD Job Market Database Hits 900+ Candidates, Open to Codex and Claude Code — aniketapanjwani · 2026-11-02
- Cron works by hand, fails on schedule: a 7-point debugging checklist — petrusenko_max · 2026-11-02
- Local quants vs Claude on 9 real private bugs: 3-bit costs thinking time, not score — FeydRowan · 2026-11-02
- Build products for AI, not humans: MCP lets Claude Code run everything — gefei55 · 2026-11-02
- Solo dev launches hosted MCP server with 31 tools scheduling to 20+ social networks — troyizzle · 2026-11-02