MICRO MOUSE BENCHMARK · REASONING MEDIUM

Gemini 4 Neon

Google · released 2026-11-18 · route gemini-4-neon · Model profile · Chess results · Sudoku results · Mines results · Nonograms results · FreeCell results · Starjar results · Nations Royale results · Wildhaven results · Hustle Sim results · Elemental Armory results · Ravelin results

Results

Score
8995%: 50 to 128 · 10 of 14 base runs so far
Campaign score against the bot
9675 to 117
Daily mazes faster than the median person
0 of 2
Reached the dock
10 of 10 mazes
Faster than the bot
2 of 10
Reached / out of time / out of replies
10 / 0 / 0
Share of the route covered, on average
100%
Wall hits per run
0.3
Drift boosts / pad boosts per run
6.1 / 0.3
Replies per run
24.6
Control segments per reply
2.34
Values moved into range
2
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
4
Model minutes per run
14.3
Tokens per reply (in / out)
3,576 / 3,566
Reasoning tokens per reply
3,533
API-equivalent cost per run
$1.58
Seconds per reply
35.0
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierAgainstRunsScoreReachedPaceWall hits / runTest pilot
Daily mazesmedian person2892 of 2890.048
Workbenchbot21022 of 21020.052
Cold Storagebot2942 of 2940.049
Fast Lanebot2912 of 2911.050
Night Shiftbot2982 of 2980.550

Every run