List your company

Mathematics on AIME 25 (Avg@32)

80.2Avg@32GLM 4.6
-1.4419.75540.9562.145Dec 30, 2025Jan 23, 2026Feb 17, 2026Mar 14, 2026Apr 7, 2026May 2, 2026May 27, 2026

Evaluation results

MethodLinks
GLM 4.6Evaluation Mode=Chat2025.1280.2
LongCat-Flash Exp-ChatEvaluation Mode=Chat2025.1274.9
LongCat-Flash ChatEvaluation Mode=Chat2025.1261.3
DeepSeek V3.2Evaluation Mode=Chat2025.1256.5
IBTPOBase Model=Qwen3-8B-Base2026.0515.3
TreeRLBase Model=Qwen3-8B-Base2026.0514.9
TreePOBase Model=Qwen3-8B-Base2026.0514.7
IBROBase Model=Qwen3-8B-Base2026.0514.5
GRPO w/ Entropy Reg†Base Model=Qwen3-8B-Base2026.0514
Vanilla GRPOBase Model=Qwen3-8B-Base2026.0513.6
GRPO w/ Clip-higherBase Model=Qwen3-8B-Base2026.0513.5
Initial ModelBase Model=Qwen3-8B-Base2026.058.9
IBTPOBase Model=Qwen3-1.7B-Base2026.056.7
TreeRLBase Model=Qwen3-1.7B-Base2026.054.6
Vanilla GRPOBase Model=Qwen3-1.7B-Base2026.054.5
GRPO w/ Clip-higherBase Model=Qwen3-1.7B-Base2026.054.5
TreePOBase Model=Qwen3-1.7B-Base2026.054.5
IBROBase Model=Qwen3-1.7B-Base2026.054.1
GRPO w/ Entropy Reg†Base Model=Qwen3-1.7B-Base2026.052.2
Initial ModelBase Model=Qwen3-1.7B-Base2026.051.7