CEval
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CEval
83.56Accuracy
67
CEval Hard
79.09Math Score
36
CEval
91.21Accuracy
31
CEval
82.16Accuracy
28
CEVAL
85.52Accuracy
23
CEval Sci
66.19Score
20
CEval
90.4Score
19
CEval
79.86Accuracy
11
CEval Discrete Math
45.56Recall
8
All Environments (Ceval-in)
0.57AER
8
Ceval
77.93Accuracy
5
CEVAL Med
91.46Accuracy
5
CEval
90.91Accuracy
4
CEval
73Accuracy
4
CEval
90.91Accuracy
4
CEVAL
58.25Accuracy (CEVAL Reasoning)
3
CEVAL
67.17CEVAL Score
3
CEval Discrete Math
12Error Rate
2
CEval
45Accuracy
2