Mathematical Reasoning on MATH (test) (BCA)
73.8BCALlama 3.1 8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 3.1 8BModel Size=8B2026.05 | 73.8 | |
| Qwen 3.5 9BModel Size=9B2026.05 | 63.4 | |
| DS-R1-7BModel Size=7B2026.05 | 63.3 | |
| Qwen2.5-32BModel Size=32B2026.05 | 62.7 | |
| DS-R1-32BModel Size=32B2026.05 | 61.4 | |
| DS-R1-14BModel Size=14B2026.05 | 60 | |
| Qwen2.5-14BModel Size=14B2026.05 | 58.1 | |
| Qwen2.5-7BModel Size=7B2026.05 | 57.9 | |
| Gemma 3 27BModel Size=27B2026.05 | 52.6 |