Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on OlymMATH
Loading...
9.3
Accuracy
NExt
4.828
5.989
7.15
8.311
Apr 13, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
NExt
#Steps=250, Backbone=Q...
2026.04
9.3
GRPO w/ FP
#Steps=250, Backbone=Q...
2026.04
8.8
GRPO w/ FP
#Steps=400, Backbone=Q...
2026.04
8.8
GRPO w/ LoRA
#Steps=400, Backbone=Q...
2026.04
8.8
GRPO w/ LoRA
#Steps=250, Backbone=Q...
2026.04
7.8
AlphaRL
#Steps=250, Backbone=Q...
2026.04
7.8
RL-Extra
#Steps=250, Backbone=Q...
2026.04
7.6
GRPO w/ FP
#Steps=400, Backbone=Q...
2026.04
6.8
NExt
#Steps=250, Backbone=Q...
2026.04
6.5
GRPO w/ FP
#Steps=250, Backbone=Q...
2026.04
6
RL-Extra
#Steps=250, Backbone=Q...
2026.04
5.8
Backbone Model
#Steps=-, Backbone=Qwe...
2026.04
5.4
Backbone Model
#Steps=-, Backbone=Qwe...
2026.04
5.3
GRPO w/ LoRA
#Steps=250, Backbone=Q...
2026.04
5
GRPO w/ LoRA
#Steps=400, Backbone=Q...
2026.04
5
AlphaRL
#Steps=250, Backbone=Q...
2026.04
5
Feedback
Search any
task
Search any
task