Mathematical Reasoning on AIME 2024 (Score)
92ScoreGLM-4.6
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-4.62025.12 | 92 | |
| INTELLECT-3Parameters=100B+2025.12 | 90.8 | |
| DeepSeek v3.22025.12 | 88.1 | |
| GLM-4.52025.12 | 85.8 | |
| GLM-4.5-Air2025.12 | 84.6 | |
| DeepSeek R1 05282025.12 | 83.2 | |
| GPT-OSSParameters=120B2025.12 | 75.8 |