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

Code Generation on MBPP (Accuracy, Avg.)

70.42Average Score

Eevee

-2.816816.196635.2154.2234May 25, 2026May 27, 2026May 30, 2026Jun 1, 2026Jun 4, 2026Jun 6, 2026Jun 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
70.42-
2026.06
69.29-
2026.06
68.2-
2026.06
67.47-
2026.05
47.8963.12
2026.05
47.2960.85
2026.05
47.0960.05
2026.05
46.7663.49
2026.05
46.3462.17
2026.05
44.6660.32
2026.05
43.3-
2026.05
42.7-
2026.05
42-
2026.05
40.5-
2026.06
38.84-
2026.05
38.8-
2026.05
36.5-
2026.05
36.5-
2026.06
35.2-
2026.06
35-
2026.06
34-
2026.06
33.2-
2026.06
33-
2026.06
32.8-
2026.06
24.4-
2026.06
23.2-
2026.06
22.8-
2026.06
19.8-
2026.06
17.8-
2026.06
0-
2026.05
-36.2
2026.05
-42
2026.05
-38.1
2026.05
-34.8
2026.05
-36.6
2026.05
-38
2026.05
-38
2026.05
-37.2
2026.05
-34.4
2026.05
-40.4
2026.05
-40.8
2026.05
-40.4
2026.05
-43.6
2026.05
-43.2
2026.05
-41.2
2026.05
-40.6
2026.05
-41.8
2026.05
-43.6
2026.05
-43
2026.05
-43.6
2026.05
-43.2