Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematics Reasoning on Math500 (Accuracy, Token Count)
Loading...
97.6
Accuracy (%)
COPT
95.936
96.368
96.8
97.232
May 19, 2026
Accuracy (%)
Token Count
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
Token Count
COPT
Backbone=Qwen3-8B, Rea...
2026.05
97.6
4,851
CoT (Greedy)
Backbone=Qwen3-8B
2026.05
96.4
5,311
COPT
Backbone=Qwen3-8B, Rea...
2026.05
96.2
3,609
CoT
Backbone=Qwen3-8B
2026.05
96
4,985
Feedback
Search any
task
Search any
task