Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematics Reasoning on GSM8K (Acc, # Tokens)
Loading...
96.36
Accuracy
COPT
95.7256
95.8903
96.055
96.2197
May 19, 2026
Accuracy
Total Tokens
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy
Total Tokens
COPT
Backbone=Qwen3-8B, Rea...
2026.05
96.36
1,813
COPT
Backbone=Qwen3-8B, Rea...
2026.05
95.98
961
CoT (Greedy)
Backbone=Qwen3-8B
2026.05
95.83
2,240
CoT
Backbone=Qwen3-8B
2026.05
95.75
2,138
Feedback
Search any
task
Search any
task