Question Answering on GPQA Diamond (198)
28.6AccuracyQwen3-14B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-14B-InstructAlignment Strategy=Base2026.03 | 28.6 | |
| Qwen3-14B-InstructAlignment Strategy=CA-aligned2026.03 | 26.6 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Qwen3-14B-InstructAlignment Strategy=Base2026.03 | 28.6 | |
| Qwen3-14B-InstructAlignment Strategy=CA-aligned2026.03 | 26.6 |