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

Overall Performance on C-Eval

42.79Accuracy

Cache-to-Cache

4.164414.192224.2234.2478Oct 3, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
42.790.39
2025.10
41.770.34
2025.10
40.770.49
2025.10
40.210.31
2025.10
38.923.59
2025.10
35.881.51
2025.10
35.270.71
2025.10
34.610.26
2025.10
32.040.26
2025.10
31.920.15
2025.10
31.310.04
2025.10
15.10.26
2025.10
5.652.02