Science Reasoning on GPQA Diamond (BCA)
81.2BCADS-R1-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| DS-R1-14BModel Size=14B2026.05 | 81.2 | |
| Qwen2.5-7BModel Size=7B2026.05 | 80.8 | |
| Qwen2.5-14BModel Size=14B2026.05 | 78.9 | |
| DS-R1-7BModel Size=7B2026.05 | 78.6 | |
| Qwen2.5-32BModel Size=32B2026.05 | 78.3 | |
| Llama 3.1 8BModel Size=8B2026.05 | 77.9 | |
| Qwen 3.5 9BModel Size=9B2026.05 | 77.3 | |
| DS-R1-32BModel Size=32B2026.05 | 76.9 | |
| Gemma 3 27BModel Size=27B2026.05 | 69.5 |