Mathematical Reasoning on USAMO AMC 12 2024 & AIME 2025 (2024-2025 latest)
1.437AMC 12 2024 ScoreDeepSeek R1
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DeepSeek R12025.01 | 1.437 | — | 256.7 | |
| OpenAI o1-12172025.01 | 1.41 | — | 261 | |
| DeepSeek V32025.01 | 0.983 | — | 131.3 | |
| GPT-4o 05132025.01 | 0.84 | — | 104 | |
| Human Participants2025.01 | 0.617 | — | 123.7 |