Mathematical Reasoning on AMC 2023 (Pass1@1)
90.39Pass@1 AccuracyDeepSearch-1.5B
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSearch-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 90.39 | |
| Nemotron-Research-Reasoning-Qwen-1.5B v2number of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 88.83 | |
| Nemotron-Research-Reasoning-Qwen-1.5B v1number of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 85.7 | |
| DeepScaleR-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 80.86 | |
| STILL-3-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 75.08 | |
| Open-RS2-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 73.52 | |
| Open-RS1-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 73.05 | |
| DeepSeek-R1-Distill-Qwen-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 72.81 | |
| Open-RS3-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 72.5 | |
| Qwen2.5-Math-1.5B-Instructnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 55.08 | |
| Qwen2.5-Math-1.5B-Oat-Zeronumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 52.5 | |
| Qwen2.5-Math-1.5Bnumber of samples=32, model scale=1.5B, evaluation cluster=128×H100 96G2025.09 | 44.06 |