Mathematics on AIME 25 (Avg@32)
80.2Avg@32GLM 4.6
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM 4.6Evaluation Mode=Chat2025.12 | 80.2 | |
| LongCat-Flash Exp-ChatEvaluation Mode=Chat2025.12 | 74.9 | |
| LongCat-Flash ChatEvaluation Mode=Chat2025.12 | 61.3 | |
| DeepSeek V3.2Evaluation Mode=Chat2025.12 | 56.5 | |
| IBTPOBase Model=Qwen3-8B-Base2026.05 | 15.3 | |
| TreeRLBase Model=Qwen3-8B-Base2026.05 | 14.9 | |
| TreePOBase Model=Qwen3-8B-Base2026.05 | 14.7 | |
| IBROBase Model=Qwen3-8B-Base2026.05 | 14.5 | |
| GRPO w/ Entropy Reg†Base Model=Qwen3-8B-Base2026.05 | 14 | |
| Vanilla GRPOBase Model=Qwen3-8B-Base2026.05 | 13.6 | |
| GRPO w/ Clip-higherBase Model=Qwen3-8B-Base2026.05 | 13.5 | |
| Initial ModelBase Model=Qwen3-8B-Base2026.05 | 8.9 | |
| IBTPOBase Model=Qwen3-1.7B-Base2026.05 | 6.7 | |
| TreeRLBase Model=Qwen3-1.7B-Base2026.05 | 4.6 | |
| Vanilla GRPOBase Model=Qwen3-1.7B-Base2026.05 | 4.5 | |
| GRPO w/ Clip-higherBase Model=Qwen3-1.7B-Base2026.05 | 4.5 | |
| TreePOBase Model=Qwen3-1.7B-Base2026.05 | 4.5 | |
| IBROBase Model=Qwen3-1.7B-Base2026.05 | 4.1 | |
| GRPO w/ Entropy Reg†Base Model=Qwen3-1.7B-Base2026.05 | 2.2 | |
| Initial ModelBase Model=Qwen3-1.7B-Base2026.05 | 1.7 |