List your company

Eating Disorder Detection on JiraiBench 1.0 (test)

79.99Macro F1SAS (English version)
37.14248.26659.3970.514Jan 8, 2026

Evaluation results

MethodLinks
SAS (English version)LLM Backbone=DeepSeek V3.22026.0179.99
Self-RefineLLM Backbone=DeepSeek V3.22026.0176.94
OWLLLM Backbone=DeepSeek V3.22026.0176.86
S^3 AgentLLM Backbone=DeepSeek V3.22026.0175.85
Zero-shotLLM Backbone=DeepSeek V3.22026.0174.15
Zero-shot CoTLLM Backbone=DeepSeek V3.22026.0173.86
SAS (English version)LLM Backbone=Gemma-3-12B-it2026.0173.8
Plan-and-SolveLLM Backbone=DeepSeek V3.22026.0172.74
SAS (English version)LLM Backbone=Ministral-3-8B2026.0169.99
S^3 AgentLLM Backbone=Gemma-3-12B-it2026.0169.06
Self-RefineLLM Backbone=Gemma-3-12B-it2026.0168.66
Self-RefineLLM Backbone=Qwen-2.5-7B2026.0161.36
Zero-shotLLM Backbone=Ministral-3-8B2026.0157.58
Zero-shot CoTLLM Backbone=Ministral-3-8B2026.0157.53
SAS (English version)LLM Backbone=Llama-3.1-8B2026.0156.42
S^3 AgentLLM Backbone=Qwen-2.5-7B2026.0155.24
Plan-and-SolveLLM Backbone=Ministral-3-8B2026.0153.96
Plan-and-SolveLLM Backbone=Qwen-2.5-7B2026.0153.17
S^3 AgentLLM Backbone=Ministral-3-8B2026.0152.99
Zero-shotLLM Backbone=Llama-3.1-8B2026.0152.95
OWLLLM Backbone=Qwen-2.5-7B2026.0152.9
Self-RefineLLM Backbone=Ministral-3-8B2026.0152.8
SAS (English version)LLM Backbone=Qwen-2.5-7B2026.0152.8
Zero-shot CoTLLM Backbone=Llama-3.1-8B2026.0152.56
Zero-shot CoTLLM Backbone=Qwen-2.5-7B2026.0152.42
OWLLLM Backbone=Ministral-3-8B2026.0150.18
Self-RefineLLM Backbone=Llama-3.1-8B2026.0149.76
Zero-shot CoTLLM Backbone=Gemma-3-12B-it2026.0147.46
Zero-shotLLM Backbone=Gemma-3-12B-it2026.0146.29
Plan-and-SolveLLM Backbone=Gemma-3-12B-it2026.0145.56
Plan-and-SolveLLM Backbone=Llama-3.1-8B2026.0145.23
Zero-shotLLM Backbone=Qwen-2.5-7B2026.0144.52
OWLLLM Backbone=Gemma-3-12B-it2026.0140.72
S^3 AgentLLM Backbone=Llama-3.1-8B2026.0139.56
OWLLLM Backbone=Llama-3.1-8B2026.0138.79