llmcoderlab

llama3.2-3b

1 run(s)16/18 graded2 failures

← all models

// score history

RunModeScore GradedFailures
run 2agentic77.99/90
run 2oneshot91.47/92

// every attempt

RunModeChallenge ScoreTestsWall
2agenticcalculator91.46/7295sreport
2agenticfizzbuzz100.03/38sreport
2agenticjson-pointer82.07/10305sreport
2agenticlru-cache76.03/5111sreport
2agenticpalindrome100.05/55sreport
2agentictemperature100.04/45sreport
2agentictext-stats0.00/167sreport
2agenticvowel-count100.05/54sreport
2agenticword-ladder52.01/5119sreport
2oneshotcalculator40.00/112sreport
2oneshotfizzbuzz100.03/34sreport
2oneshotjson-pointerdegenerate7sreport
2oneshotlru-cache100.05/56sreport
2oneshotpalindrome100.05/53sreport
2oneshottemperature100.04/43sreport
2oneshottext-statsdegenerate6sreport
2oneshotvowel-count100.05/52sreport
2oneshotword-ladder100.05/59sreport