Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Coding on HumanEval (mean score)

0.9695HumanEval Mean Score

Ministral-3-R

-0.007580.2460850.499750.753415Jan 21, 2026Jan 30, 2026Feb 8, 2026Feb 17, 2026Feb 26, 2026Mar 7, 2026Mar 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
0.9695
2026.02
0.9634
2026.02
0.9512
2026.01
0.945
2026.02
0.939
2026.02
0.939
2026.01
0.933
2026.02
0.9146
2026.01
0.823
2026.01
0.823
0.817
2026.01
0.799
2026.01
0.793
2026.01
0.75
2026.01
0.72
2026.01
0.689
2026.01
0.671
2026.01
0.64
2026.01
0.634
2026.01
0.616
2026.01
0.616
2026.01
0.61
2026.01
0.61
2026.01
0.567
2026.01
0.506
2026.03
0.4634
2026.03
0.4512
2026.03
0.415
2026.01
0.384
2026.01
0.378
2026.03
0.378
2026.01
0.03