Evaluation Alignment on ASAP 2.0
0.7276QWKRULERS
Evaluation Results
| Method | Links | |
|---|---|---|
| RULERSBackbone=GPT-4o-mini2026.01 | 0.7276 | |
| RULERSBackbone=Llama-3.1-70B2026.01 | 0.7179 | |
| RULERSBackbone=GPT-4o2026.01 | 0.7122 | |
| RULERSBackbone=Llama-3.1-8B2026.01 | 0.6826 | |
| MTSBackbone=GPT-4o-mini2026.01 | 0.5566 | |
| DHSBackbone=Llama-3.1-70B2026.01 | 0.4986 | |
| MTSBackbone=GPT-4o2026.01 | 0.4939 | |
| AutoScoreBackbone=GPT-4o-mini2026.01 | 0.4653 | |
| AutoScoreBackbone=Llama-3.1-70B2026.01 | 0.4591 | |
| MTSBackbone=Llama-3.1-70B2026.01 | 0.4333 | |
| DHSBackbone=GPT-4o-mini2026.01 | 0.4319 | |
| AutoScoreBackbone=GPT-4o2026.01 | 0.3912 | |
| MTSBackbone=Llama-3.1-8B2026.01 | 0.3716 | |
| AutoScoreBackbone=Llama-3.1-8B2026.01 | 0.3548 | |
| DHSBackbone=GPT-4o2026.01 | 0.35 | |
| DHSBackbone=Llama-3.1-8B2026.01 | 0.1546 |