SupermavenvsZhanlu
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Supermaven
Supermaven (Cursor / Anysphere) · IDE extension
#273
Panel
2.71 spec wins
- Reliability
- 3.5
- Usefulness
- 2.8
- Cost
- 3.2
- Longevity
- 1.3
“Built by the inventor of Tabnine, bought by Cursor, and now a changelog entry for Cursor Tab.”
Zhanlu
China Mobile Cloud · IDE extension
#265MCP
Panel
3.53 spec wins
- Reliability
- 3.3
- Usefulness
- 4.3
- Cost
- 2.8
- Longevity
- 3.5
“One of its modes generates practice problems, so it can now set the homework and then do it for you.”
Spec by spec
| Spec | Supermaven | Zhanlu |
|---|---|---|
| Architecture | ||
| Category | IDE extension | IDE extension |
| Runs | local | local |
| Platforms | macos, linux, windows | macos, linux, windows |
| Context window | 1M tokens | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | No |
| Capabilities | ||
| Runs terminal commands | No | YesDocumented only for AI Programmer mode, which the vendor says saves and executes the code it writes and then debugs it. |
| Multi-file edits | No | YesAI Programmer mode supports file editing and project-level code generation across files; the other modes work on the selected snippet. |
| Git operations | No | No |
| Browser control | No | No |
| Sandboxed execution | No | No |
| Multi-agent orchestration | No | No |
| Headless / CI mode | No | No |
| Models | ||
| Backbone | Supermaven, GPT-4o, Claude 3.5 Sonnet | Zhanlu code model |
| Bring your own model | No | No |
| Local models | No | No |
| Cost | ||
| Pricing model | subscription | mixed |
| Starts at | $10/mo | n/a |
| Free tier | Yes | No |
| Bring your own key | No | No |
| Openness | ||
| Open source | No | No |
| License | proprietary | proprietary |
| GitHub stars | 1,458 | n/a |
Which one would each critic pick
| Critic | Supermaven | Zhanlu | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 3.3 | 4.0 | Zhanlu — Pick it only if you already work inside this cloud; for everyone else the account requirement decides the question before any feature does. |
| El Crítico | 2.8 | 3.5 | Zhanlu — The extension is built on two open-source codebases, which the vendor credits, and shipped closed, so upstream fixes and local divergence are both unobservable. |
| El Profesor | 4.0 | 3.3 | Supermaven — The 1M-token completion context was the design claim and it was never measured publicly; the chat panel used GPT-4o and Claude 3.5 Sonnet, so the proprietary model only covered autocomplete. |
| La Inversora | 2.3 | 4.8 | Zhanlu — Thirty-six thousand editor installations since June 2024, given away by a telecommunications cloud that charges for the account you need to use it. |
| La Jefa | 1.8 | 2.8 | Zhanlu — No price is published, use requires a registration on a portal that is not reachable from here, and there is no console, single sign-on or audit export. |
| El Hacker | 2.3 | 2.8 | Zhanlu — Closed source, one vendor model, no key of my own and no local weights, so the only thing I can configure is which tool servers it may call. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.