Share your thoughts, 1 month free Claude Pro on usSee more

Mathematical Reasoning on AIME24 (Total inference runtime)

0Total Inference Runtime (mm:ss)

S-GRPO

Updated 12d ago

Evaluation Results

Method	Links
S-GRPO 2026.04		0
RED 2026.04		0
S-GRPO 2026.04		0
DAST 2026.04		1
RL +length penalty 2026.04		1
S-GRPO 2026.04		1
RED 2026.04		1
Think or Not 2026.04		1
DAST 2026.04		1
RL +length penalty 2026.04		1
S-GRPO 2026.04		1
RL +length penalty 2026.04		1
RED 2026.04		1
Vanilla 2026.04		2
Think or Not 2026.04		2
DAST 2026.04		2
RL +length penalty 2026.04		2
RED 2026.04		2
Vanilla 2026.04		2
DAST 2026.04		2
RL +length penalty 2026.04		2
RED 2026.04		2
Vanilla 2026.04		2
Think or Not 2026.04		2
DAST 2026.04		2
S-GRPO 2026.04		3
RED 2026.04		3
Vanilla 2026.04		4
Think or Not 2026.04		4
Vanilla 2026.04		4
Think or Not 2026.04		4
DAST 2026.04		5
RL +length penalty 2026.04		5
S-GRPO 2026.04		5
Vanilla 2026.04		6
Think or Not 2026.04		6