Evaluation Alignment on SummHF
0.3954QWKRULERS
Evaluation Results
| Method | Links | |
|---|---|---|
| RULERSBackbone=Llama-3.1-70B2026.01 | 0.3954 | |
| MTSBackbone=Llama-3.1-70B2026.01 | 0.3915 | |
| AutoScoreBackbone=Llama-3.1-70B2026.01 | 0.383 | |
| RULERSBackbone=GPT-4o2026.01 | 0.3577 | |
| RULERSBackbone=GPT-4o-mini2026.01 | 0.3367 | |
| DHSBackbone=Llama-3.1-70B2026.01 | 0.3329 | |
| MTSBackbone=GPT-4o2026.01 | 0.3273 | |
| MTSBackbone=GPT-4o-mini2026.01 | 0.3219 | |
| AutoScoreBackbone=GPT-4o2026.01 | 0.3215 | |
| DHSBackbone=GPT-4o2026.01 | 0.2965 | |
| AutoScoreBackbone=GPT-4o-mini2026.01 | 0.2883 | |
| DHSBackbone=GPT-4o-mini2026.01 | 0.2599 | |
| RULERSBackbone=Llama-3.1-8B2026.01 | 0.1464 | |
| MTSBackbone=Llama-3.1-8B2026.01 | 0.1304 | |
| AutoScoreBackbone=Llama-3.1-8B2026.01 | 0.1241 | |
| DHSBackbone=Llama-3.1-8B2026.01 | 0.0941 |