HUSTLE SIM BENCHMARK · LOCAL, NO THINKING

Gemma 3 4B

Google · open weights · released 2025-03-12 · route gemma3:4b · Model profile · Chess results · Sudoku results · FreeCell results · Elemental Armory results

Results

Score
795%: 0 to 45 · 2 of 6 base runs so far
Reached the goal in time
1 of 2 runs
Ran out of replies / forfeited / never
1 / 0 / 0
Game time over the best line's
18.3x
As fast as the best line or faster
0 of 2 runs
Decisions per run
22.0
Actions per decision
5.07
Purchases the game refused
121 of 223 (54.3%)
Decisions with no readable actions
2.3%
Retries for a reply with no actions tag
7
Tokens per decision (in / out)
1,967 / 46
Reasoning tokens per decision
n/a
Model minutes per run
4.0
Runs on other rules (not counted)
0
API-equivalent cost per run
n/a
Seconds per decision
10.9
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierGoalRepliesRunsScoreMedian time vs bestIn time / ran out / never
Fresh start$1M301310h 56m vs 17m 30s0 / 1 / 0
Takeover$1B601113d 2h vs 8h 24m1 / 0 / 0
Empire$1T800n/anever vs never0 / 0 / 0

Against the game's strategies, run by run

Runs where it reached the goal sooner than each strategy did from the same start.

StrategyFaster
Best income per dollar0 of 2
Deepen first0 of 2
Cheapest thing available0 of 2
Chase speed milestones0 of 2
Perks before levels2 of 2
Automate everything2 of 2
Collect first2 of 2
Unguided (seed 3)2 of 2
Unguided (seed 1)2 of 2
Unguided (seed 2)2 of 2

Every run