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

Code Generation on HumanEval (HumanEval and Average metrics)

94.51HumanEval Score

FinTool-Qwen3-14B

-3.780421.737347.25572.7727Mar 13, 2026Mar 18, 2026Mar 24, 2026Mar 29, 2026Apr 4, 2026Apr 9, 2026Apr 15, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.03
94.51-
2026.03
92.68-
2026.03
89.63-
2026.03
89.02-
2026.03
55.755.3
2026.03
5537.7
2026.03
54.255.5
2026.03
53.852.6
2026.03
5252.3
2026.03
51.753.4
2026.03
51.350.1
2026.03
51.353
2026.03
50.650.2
2026.03
50.149.3
2026.03
49.756.3
2026.03
48.447.3
2026.03
48.448.1
2026.03
46.344.3
2026.03
44.541.6
2026.03
43.845.3
2026.03
43.142.5
2026.03
41.746.8
2026.03
41.350.4
2026.04
34.7646.1
2026.03
33.538.4
2026.04
30.49-
2026.04
30.49-
2026.04
30.49-
2026.04
29.27-
2026.03
28.643
2026.04
28.05-
2026.04
28.05-
2026.04
27.1237.54
2026.04
27.0537.48
2026.04
26.83-
2026.03
26.534
2026.04
26.22-
2026.04
25.66-
2026.04
25-
2026.04
24.39-
2026.04
24.39-
2026.04
23.8630.6
2026.04
23.17-
2026.04
22.56-
2026.04
22.56-
2026.04
22.1228.8
2026.04
21.34-
2026.04
21.34-
2026.04
20.73-
2026.04
20.2326.94
2026.04
19.51-
2026.04
19.31-
2026.04
18.9-
2026.04
18.29-
2026.04
18.1222.56
2026.04
17.68-
2026.04
17.2-
2026.04
17.07-
2026.04
17.07-
2026.04
16.46-
2026.04
16.46-
2026.04
15.85-
2026.04
15.85-
2026.04
15.75-
2026.04
14.02-
2026.04
13.8816.96
2026.04
13.41-
2026.04
11.59-
2026.04
11.59-
2026.04
10.9833.45
2026.04
10.2-
2026.04
9.7315.1
2026.03
9.729.9
2026.04
9.02-
2026.04
8.54-
2026.04
7.2824.85
2026.04
6.83-
2026.04
6.3324.54
2026.04
5.49-
2026.04
4.27-
2026.04
3.13-
2026.04
2.31-
2026.04
2.0116.97
2026.04
0.4214.85
2026.04
0.0211.77
2026.04
0-
2026.04
0-
2026.04
0-
2026.04
03.88
2026.04
01.9
2026.04
06.07
2026.04
09.69
2026.04
012.1