List your company

User preference prediction on Steam Pref (test)

73.6AccuracyEP+SEM_CRIT
51.55257.2766368.724Oct 22, 2025

Evaluation results

MethodLinks
EP+SEM_CRITModel=gpt-4o-mini-2024-07-182025.1073.6
EP_CRITModel=gpt-4o-mini-2024-07-182025.1071.2
EP_CRITModel=gpt-5-2025-08-072025.1069.2
EP_CRITModel=gpt-5-2025-08-072025.1069.2
EP+SEM_CRITModel=gpt-5-2025-08-072025.1068.8
EP+SEM_CRITModel=gpt-5-2025-08-072025.1068.8
EP_CRITModel=qwen3-235b-a22b-instruct-25072025.1068.4
EP+SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.1068.4
EP_LABELModel=llama-4-scout2025.1066.8
EP_LABELModel=gpt-5-2025-08-072025.1064.4
SEM_CRITModel=gpt-5-2025-08-072025.1064.4
EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.1064.4
EP_LABELModel=gpt-5-2025-08-072025.1064.4
SEM_CRITModel=gpt-5-2025-08-072025.1064.4
EP_CRITModel=qwen3-vl-235b-a22b-thinking2025.1064.4
SEM_CRITModel=qwen3-235b-a22b-instruct-25072025.1064
EP+SEM_CRITModel=llama-4-scout2025.1063.6
EP_CRITModel=gpt-oss-20b2025.1063.2
SEM_CRITModel=llama-4-scout2025.1063.2
EP_CRITModel=gpt-oss-20b2025.1063.2
EP+SEM_CRITModel=gpt-oss-20b2025.1062.8
EP+SEM_CRITModel=gpt-oss-20b2025.1062.8
EP_CRITModel=llama-4-scout2025.1062.4
EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.1062
EP+SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.1062
EP_LABELModel=gpt-4o-mini-2024-07-182025.1061.2
SEM_CRITModel=gpt-4o-mini-2024-07-182025.1060.4
zero_shotModel=qwen3-vl-235b-a22b-thinking2025.1058.8
zero_shotModel=qwen3-vl-235b-a22b-thinking2025.1058.8
zero_shotModel=gpt-4o-mini-2024-07-182025.1058.4
EP_LABELModel=gpt-oss-20b2025.1057.2
SEM_CRITModel=gpt-oss-20b2025.1057.2
SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.1057.2
EP_LABELModel=gpt-oss-20b2025.1057.2
SEM_CRITModel=gpt-oss-20b2025.1057.2
SEM_CRITModel=qwen3-vl-235b-a22b-thinking2025.1057.2
EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.1056.6
EP_LABELModel=qwen3-vl-235b-a22b-thinking2025.1056.6
zero_shotModel=llama-4-scout2025.1056.4
EP_LABELModel=qwen3-235b-a22b-instruct-25072025.1055.6
zero_shotModel=qwen3-235b-a22b-instruct-25072025.1054.8
zero_shotModel=gpt-5-2025-08-072025.1053.6
zero_shotModel=gpt-5-2025-08-072025.1053.6
zero_shotModel=gpt-oss-20b2025.1052.4
zero_shotModel=gpt-oss-20b2025.1052.4