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

Code Generation on MBPP (Acc, TPF, AUP)

63.6Accuracy

Qwen-2.5-7B-it

9.93623.86837.851.732Mar 4, 2026Mar 17, 2026Mar 30, 2026Apr 12, 2026Apr 25, 2026May 8, 2026May 21, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.03
63.6163.6--
2026.03
60.25.69298.6--
2026.03
58.311.1641.6--
2026.03
582.4481.1--
2026.03
57.2157.2--
2026.03
55.62.96141.4--
2026.03
55.42.24108--
2026.03
53.21.263.6--
2026.03
50.12.0481.9--
2026.03
47.1147.1--
2026.05
41.7141.7--
2026.05
41.63.3889.3--
2026.03
40.64.2188.4--
2026.05
40.64.2188.4--
2026.05
40.63.4280.3--
2026.03
402.3560.5--
2026.05
402.3560.5--
2026.03
38.62.1356.6--
2026.05
38.62.1356.6--
2026.03
381.9450--
2026.05
381.9453--
2026.05
21----
2026.05
17----
2026.05
12----
2026.05
---36.4-
2026.05
---37-
2026.05
---34.27-
2026.05
---37.2-
2026.05
---27-
2026.05
---38.6-
2026.05
---4752.3
2026.05
---46.653.1
2026.05
---4954.7
2026.05
---5056.3
2026.05
---50.456.7
2026.05
---61.470.8
2026.05
---53.269.7
2026.05
---55.671.1
2026.05
---57.471.6
2026.05
---63.274.3
2026.05
---3743
2026.05
---36.444.8
2026.05
---36.445.4
2026.05
---3745.9
2026.05
---3847