Agent · Alibaba · cli
Qwen Code
12
tools registered
5/6
compared capabilities
it has a tool for
it has a tool for
3
of those tools
read from source
read from source
Qwen Code registers 12 tools, covering 5 of 6 compared capabilities. It registers no built-in tool for browser.
Surface size
tools registered, across the 13 harnesses hereSurface size, not quality. Every registered tool spends context on every request, so a longer bar is a cost as much as a capability — and a harness that reaches a capability through a general tool may register fewer.
Capabilities
what serves each, and where it is compared| Capability | Tools | Across harnesses |
|---|---|---|
| Read | read_file | 13 of 13 have one → |
| Browser | no built-in tool | 3 of 13 have one → |
| Web search | web_search | 9 of 13 have one → |
| Code search | globpartial · grep_search | 13 of 13 have one → |
| Shell | run_shell_command | 13 of 13 have one → |
| Long-term memory | save_memory | 4 of 13 have one → |
Where its tools differ from the rest
- glob · Glob syntaxglob library patternsvs ripgrep --glob in 4 of 7
- grep_search · Regex dialectvaries by backend: Rust regex, git grep, POSIX, or JS RegExpvs Rust regex in 8 of 10
- grep_search · Search line N is read line Ninvariantfailsvs holds in 6 of 6
- grep_search · Case sensitivityalways insensitive, not configurablevs sensitive, model can ask in 3 of 5
- read_file · Offset base0-indexedvs 1-indexed in 7 of 7
Derived by comparing every recorded value against the other implementations of the same capability. Differing is not a defect unless the row is marked an invariant.
All 12 tools
names verbatim, as registeredNot yet compared
Not yet compared means registered by Qwen Code but with no comparison page here — todo lists, subagent spawning, approval flows. They become capabilities the day there is a comparison worth reading, and the data does not have to change for that to happen.
pi
ZCode →