List your company

Overdose Detection on JiraiBench 1.0 (test)

0.7743Macro F1S^3 Agent
0.2645960.3969230.529250.661577Jan 8, 2026

Evaluation results

MethodLinks
S^3 AgentLLM Backbone=DeepSeek V3.22026.010.7743
Self-RefineLLM Backbone=DeepSeek V3.22026.010.7652
SAS (English version)LLM Backbone=DeepSeek V3.22026.010.7505
Zero-shotLLM Backbone=DeepSeek V3.22026.010.7325
Zero-shot CoTLLM Backbone=DeepSeek V3.22026.010.7235
Plan-and-SolveLLM Backbone=DeepSeek V3.22026.010.7025
Self-RefineLLM Backbone=Gemma-3-12B-it2026.010.6549
OWLLLM Backbone=DeepSeek V3.22026.010.6397
Zero-shot CoTLLM Backbone=Ministral-3-8B2026.010.6338
Zero-shotLLM Backbone=Ministral-3-8B2026.010.6314
Plan-and-SolveLLM Backbone=Ministral-3-8B2026.010.6294
OWLLLM Backbone=Ministral-3-8B2026.010.5855
Self-RefineLLM Backbone=Qwen-2.5-7B2026.010.5785
S^3 AgentLLM Backbone=Gemma-3-12B-it2026.010.5769
S^3 AgentLLM Backbone=Ministral-3-8B2026.010.5727
SAS (English version)LLM Backbone=Gemma-3-12B-it2026.010.5685
SAS (English version)LLM Backbone=Ministral-3-8B2026.010.5672
SAS (English version)LLM Backbone=Qwen-2.5-7B2026.010.5613
OWLLLM Backbone=Gemma-3-12B-it2026.010.553
Self-RefineLLM Backbone=Ministral-3-8B2026.010.5483
Zero-shotLLM Backbone=Qwen-2.5-7B2026.010.5206
Zero-shotLLM Backbone=Gemma-3-12B-it2026.010.515
Zero-shot CoTLLM Backbone=Gemma-3-12B-it2026.010.509
S^3 AgentLLM Backbone=Qwen-2.5-7B2026.010.5084
Plan-and-SolveLLM Backbone=Gemma-3-12B-it2026.010.5082
OWLLLM Backbone=Qwen-2.5-7B2026.010.5015
Zero-shot CoTLLM Backbone=Qwen-2.5-7B2026.010.4759
Plan-and-SolveLLM Backbone=Qwen-2.5-7B2026.010.473
SAS (English version)LLM Backbone=Llama-3.1-8B2026.010.4384
Self-RefineLLM Backbone=Llama-3.1-8B2026.010.4221
Zero-shotLLM Backbone=Llama-3.1-8B2026.010.3622
S^3 AgentLLM Backbone=Llama-3.1-8B2026.010.3463
OWLLLM Backbone=Llama-3.1-8B2026.010.3457
Zero-shot CoTLLM Backbone=Llama-3.1-8B2026.010.3308
Plan-and-SolveLLM Backbone=Llama-3.1-8B2026.010.2842