llmcoderlab

qwen2.5-coder-3b

2 run(s)21/28 graded7 failures

← all models

// score history

RunModeScore GradedFailures
run 2agentic49.89/90
run 2oneshot87.24/95
run 1agentic80.05/50
run 1oneshot100.03/52

// every attempt

RunModeChallenge ScoreTestsWall
2agenticcalculator48.61/7341sreport
2agenticfizzbuzz100.03/3129sreport
2agenticjson-pointer0.00/1139sreport
2agenticlru-cache0.00/1239sreport
2agenticpalindrome100.05/563sreport
2agentictemperature100.04/477sreport
2agentictext-stats0.00/1384sreport
2agenticvowel-count100.05/563sreport
2agenticword-ladder0.00/1228sreport
2oneshotcalculator48.61/716sreport
2oneshotfizzbuzz100.03/36sreport
2oneshotjson-pointerdegenerate6sreport
2oneshotlru-cachedegenerate6sreport
2oneshotpalindromedegenerate3sreport
2oneshottemperature100.04/45sreport
2oneshottext-statsdegenerate14sreport
2oneshotvowel-count100.05/53sreport
2oneshotword-ladderdegenerate12sreport
1agenticfizzbuzz100.03/390sreport
1agenticpalindrome100.05/541sreport
1agentictemperature100.04/451sreport
1agentictext-stats0.00/1251sreport
1agenticvowel-count100.05/541sreport
1oneshotfizzbuzz100.03/36sreport
1oneshotpalindromeerror3sreport
1oneshottemperature100.04/42sreport
1oneshottext-statserror8sreport
1oneshotvowel-count100.05/52sreport