List your company

Causality Discovery OOD Evaluation

100Success RateGPT-4.1-2025-04-14
-2.02424.46350.9577.437Sep 29, 2025

Evaluation results

MethodLinks
GPT-4.1-2025-04-142025.0910035.9
Mistral-Small-3.1-24B-Ins2025.0910025.8
Qwen2.5-Instruct-7B2025.0910026.3
Llama-3.1-70B-Instruct2025.0999.928.9
TIMEOMNI-1Base LLM=Qwen2.5-Instruct-7B2025.0999.864
GPT-4.1-Nano2025.0998.428
Mistral-7B-v0.32025.0982.626.9
Time-MQABase LLM=Mistral-7B-v0.32025.0952.24
Time-R1Base LLM=Qwen2.5-Instruct-7B2025.0948.931.4
Time-MQABase LLM=Llama3-8B2025.0937.231.2
Time-MQABase LLM=Qwen2.5-7B2025.093230.5
ChatTS2025.0926.718.6
Llama-3.1-8B-Instruct2025.091.9—