List your company

Evaluation Alignment on SummHF

0.3954QWKRULERS
0.0820480.1633990.244750.326101Jan 13, 2026

Evaluation results

MethodLinks
RULERSBackbone=Llama-3.1-70B2026.010.3954
MTSBackbone=Llama-3.1-70B2026.010.3915
AutoScoreBackbone=Llama-3.1-70B2026.010.383
RULERSBackbone=GPT-4o2026.010.3577
RULERSBackbone=GPT-4o-mini2026.010.3367
DHSBackbone=Llama-3.1-70B2026.010.3329
MTSBackbone=GPT-4o2026.010.3273
MTSBackbone=GPT-4o-mini2026.010.3219
AutoScoreBackbone=GPT-4o2026.010.3215
DHSBackbone=GPT-4o2026.010.2965
AutoScoreBackbone=GPT-4o-mini2026.010.2883
DHSBackbone=GPT-4o-mini2026.010.2599
RULERSBackbone=Llama-3.1-8B2026.010.1464
MTSBackbone=Llama-3.1-8B2026.010.1304
AutoScoreBackbone=Llama-3.1-8B2026.010.1241
DHSBackbone=Llama-3.1-8B2026.010.0941