SUDOKU BENCHMARK · LOCAL, NO THINKING

Gemma 3 4B

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

Results

Score
095%: 0 to 20 · 7 of 42 grids so far
Grids solved
0 of 7
Blank cells filled correctly
6.7%
Wrong cells / empty cells / changed a given / no grid
0 / 0 / 5 / 2
Broke the rules (complete grid repeating a digit)
0
Near misses (three cells or fewer wrong)
0
Average stated confidence
96%
Average confidence when it had not solved it
96%
Sure but wrong (90% or more, unsolved)
7
Calibration (Brier, lower is better)
0.925
API-equivalent cost per grid
n/a
API-equivalent cost per solved grid
n/a
Seconds per grid
18
Tokens per grid (in / out)
464 / 177
Reasoning tokens per grid
n/a
Retries for an unreadable reply
2
Aborted on our side (not counted)
0

By tier

TierNeedsSolvedOutput tokensSeconds
CozySingles only0 of 114216
GentleScanning0 of 129515
SteadyLocked candidates0 of 113314
TrickyHidden pairs and triples0 of 125937
DeviousWings and fish0 of 11327
ExpertDeep wings and fish0 of 114924
BeyondNo human technique finishes it0 of 112714

Cells by the technique they needed

Each blank cell is tagged with the simplest technique that fills it, given everything a solver could fill before it.

TechniqueCellsFilled correctly
Last free cell6111.5%
Scanning7910.1%
Locked candidates460.0%
Hidden pairs and triples1100.0%
Wings and fish229.1%
Deep wings and fish3414.7%
Search339.1%

Every answer