List your company

Natural Language Inference on ANLI and HANS (unseen)

32.4ANLI ScoreQwen 2.5 7B
26.1627.7829.431.02May 21, 2025

Evaluation results

MethodLinks
Qwen 2.5 7BK=7, type=Baseline2025.0532.484.458.4
FOVER-Qwen2.5-7B-PRMK=7, Base Model=Qwen 2.5 7B2025.0530.88658.4
FOVER-Llama3.1-8B-PRMK=7, Base Model=Llama 3.1 8B2025.053081.255.6
Qwen2.5-Math-7B-PRM800KK=7, Base Model=Qwen 2.5 7B2025.0529.683.256.4
Qwen2.5-7B-Skywork-PRMK=7, Base Model=Qwen 2.5 7B2025.0529.281.255.2
Qwen2.5-Math-PRM-7BK=7, Base Model=Qwen 2.5 7B2025.0527.68656.8
RLHFlow-Llama3.1-8B-DK=7, Base Model=Llama 3.1 8B2025.0527.274.450.8
RLHFlow-Llama3.1-8B-MK=7, Base Model=Llama 3.1 8B2025.0526.877.652.2
Llama 3.1 8BK=7, type=Baseline2025.0526.469.247.8