List your company

Mathematics on AIME 24

83.7Avg@32GLM 4.6
-3.3084819.2802641.86964.45774Dec 30, 2025Jan 23, 2026Feb 17, 2026Mar 14, 2026Apr 7, 2026May 2, 2026May 27, 2026

Evaluation results

MethodLinks
GLM 4.6Evaluation Mode=Chat2025.1283.7
LongCat-Flash Exp-ChatEvaluation Mode=Chat2025.1283.1
DeepSeek V3.2Evaluation Mode=Chat2025.1273.9
LongCat-Flash ChatEvaluation Mode=Chat2025.1270.4
IBTPOBase Model=Qwen3-8B-Base2026.050.197
TreeRLBase Model=Qwen3-8B-Base2026.050.178
TreePOBase Model=Qwen3-8B-Base2026.050.175
Vanilla GRPOBase Model=Qwen3-8B-Base2026.050.171
GRPO w/ Entropy Reg†Base Model=Qwen3-8B-Base2026.050.17
IBROBase Model=Qwen3-8B-Base2026.050.169
GRPO w/ Clip-higherBase Model=Qwen3-8B-Base2026.050.168
Initial ModelBase Model=Qwen3-8B-Base2026.050.115
IBTPOBase Model=Qwen3-1.7B-Base2026.050.095
TreeRLBase Model=Qwen3-1.7B-Base2026.050.079
GRPO w/ Clip-higherBase Model=Qwen3-1.7B-Base2026.050.077
TreePOBase Model=Qwen3-1.7B-Base2026.050.072
Vanilla GRPOBase Model=Qwen3-1.7B-Base2026.050.07
GRPO w/ Entropy Reg†Base Model=Qwen3-1.7B-Base2026.050.066
IBROBase Model=Qwen3-1.7B-Base2026.050.056
Initial ModelBase Model=Qwen3-1.7B-Base2026.050.038