Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on ORZ-57K, AIME24/25, Minerva, Math500, AMC, OlympiadBench (test)
Loading...
31.66
Accuracy (Minerva)
ACPO
12.5864
17.5382
22.49
27.4418
Jun 21, 2026
Accuracy (Minerva)
Accuracy (Math500)
Accuracy (AMC)
Accuracy (AIME24)
Accuracy (AIME25)
Accuracy (Olympiad)
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Minerva)
Accuracy (Math500)
Accuracy (AMC)
Accuracy (AIME24)
Accuracy (AIME25)
Accuracy (Olympiad)
Average Accuracy
ACPO
Backbone=Qwen2.5-7B, P...
2026.06
31.66
80.48
51.2
16.35
10.1
42.17
38.66
ACPO
Backbone=Qwen2.5-7B, P...
2026.06
31.02
79.78
54.37
16.77
14.37
42.83
39.86
Base Model
Backbone=Qwen2.5-7B, P...
2026.06
13.32
41.48
26.2
0.83
0.62
18.02
16.75
Feedback
Search any
task
Search any
task