Bolt.new vs Claude Code
Direct comparison of Bolt.new (from StackBlitz) and Claude Code (from Anthropic). Want a 3- or 4-way comparison? Open the multi-agent tool →
| Bolt.new StackBlitz | Claude Code Anthropic | |
|---|---|---|
| Overview | ||
| Vendor | StackBlitz | Anthropic |
| Category | coding | coding |
| Release date | — | — |
| Source | proprietary | proprietary |
| License | — | — |
| Pricing | Free tier · $20/mo Pro | Included with Claude Pro/Max/Team subscriptions |
| Base models | — | |
| Capabilities | in_browser_runtimeapp_generationwebcontainers | terminalfile_iomulti_file_editshell_exec+1 |
| Capability | ||
| gpt.buzz Index | — | 95.4 |
| SWE-bench Verified | — | 80.9% |
| SWE-bench Pro | — | 55.4% |
| Terminal-Bench 2.0 | — | 65.4% |
| GAIA | — | 74.6% |
| WebArena | — | 64.5% |
| Adoption | ||
| OpenRouter · daily | — | 51.6B |
| OpenRouter · cumulative | — | 3.52T |
| GitHub stars | — | — |
| Links | ||
| Links | ||
More on each
Full agent profiles — Bolt.new / Claude Code
Or browse the full agent directory / composite leaderboard.