MICRO MOUSE BENCHMARK · REASONING MEDIUM

Gemini 4 Argon

Google · released 2026-09-30 · route gemini-4-argon · Model profile · Chess results · Mines results · Nonograms results · FreeCell results · Starjar results · Nations Royale results · Hustle Sim results · Elemental Armory results · Ravelin results

Results

Score
5295%: 23 to 81 · 5 of 14 base runs so far
Campaign score against the bot
6849 to 87
Daily mazes faster than the median person
0 of 1
Reached the dock
5 of 5 mazes
Faster than the bot
0 of 5
Reached / out of time / out of replies
5 / 0 / 0
Share of the route covered, on average
100%
Wall hits per run
15.2
Drift boosts / pad boosts per run
1.2 / 0.4
Replies per run
30.8
Control segments per reply
2.77
Values moved into range
35
Segments cut at the one-second limit
0
Lines that were not segments
0
Replies with no readable segment
0.0%
Retries for an unreadable reply
0
Model minutes per run
4.6
Tokens per reply (in / out)
3,509 / 176
Reasoning tokens per reply
109
API-equivalent cost per run
$0.271
Seconds per reply
8.9
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierAgainstRunsScoreReachedPaceWall hits / runTest pilot
Daily mazesmedian person1521 of 15214.048
Workbenchbot1571 of 15722.052
Cold Storagebot1601 of 16014.049
Fast Lanebot1801 of 18010.050
Night Shiftbot1761 of 17616.050

Every run