Curiosity ComparisonBetween Agents
A third coding agent joins the context ladder. Gemini tops the curiosity index at 100 against Claude's 60 and Codex's 23, spends 38% of its actions reading files, and is the only one of the three that explores more as the workspace gets richer.
9 beats · 11 min to read in full
Two studies ago we called itthe incurious agent: coding agents
Two studies ago we called it the incurious agent: coding agents that skim the surface of a workspace and skip the substance. We added a third agent to the same test, Google's Gemini, and, for the first time, the pattern breaks.
Condensed from the note.
A third agenton the ladder
The setup is the one we've used throughout this series, kept deliberately small so the behavior is easy to read.
E0: the bare repository
code only.
E1: + README.
E2: + AGENTS.md (an operating contract).
E3: + PROJECT.md (a project brief).
Condensed from the note, which carries 7 points.
The agentthat opens files
Start with the simplest possible question, the one the whole series turns on: when an agent sits down in a workspace, does it actually open anything?
share of actions spent reading files, indexed so the most curious agent is 100. Gemini: measured 100. Claude: measured 60. Codex: measured 23.
Condensed from the note.
Curiosity that growswith the room
A skeptic could ask whether Gemini just has a fixed appetite for files, that it would read the same amount no matter what's in front of it. It doesn't.
Condensed from the note.
Curiosity you can seein the work
None of this would matter if the reading were idle. It isn't. Gemini's curiosity shows up as genuine engagement with the workspace, and then in the result.
Condensed from the note.
Curiosity,finally
Put the three charts together and one trait explains all of them.
Condensed from the note.
How to readthis honestly
This is a small, controlled probe, and the caveats shape the claim.
A single run per rung, one small repository, one task.
These are directional behaviors, not tight confidence intervals: enough to see a clean, repeated separation in reading habits, not enough to rank the fine details.
The deepest context stayed unopened by all three.
No agent in this run cracked the seeded memory/ tree specifically; the curiosity we measured is Gemini opening source and project files far more than its rivals, not evidence that any agent yet mines…
Thoroughness has a price.
Reading costs tokens, and Gemini's habit of opening files makes it dearer than an agent that greps and leaves.
Condensed from the note.
That is the note,in one pass.
This is Curiosity Comparison Between Agents condensed to its beats. The full note carries every paragraph, the tables, the code, and the source it was adapted from.