Decision Making on Decision Making OOD
58.9ACCTIMEOMNI-1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TIMEOMNI-1Base LLM=Qwen2.5-Instruct-7B2025.09 | 58.9 | 100 | |
| Mistral-Small-3.1-24B-Ins2025.09 | 42.9 | 100 | |
| GPT-4.1-Nano2025.09 | 34.1 | 97.8 | |
| Time-R1Base LLM=Qwen2.5-Instruct-7B2025.09 | 32.2 | 93.1 | |
| GPT-4.1-2025-04-142025.09 | 27.8 | 100 | |
| Time-MQABase LLM=Qwen2.5-7B2025.09 | 26.4 | 44.3 | |
| Qwen2.5-Instruct-7B2025.09 | 24.9 | 100 | |
| Llama-3.1-70B-Instruct2025.09 | 17.7 | 97.4 | |
| Mistral-7B-v0.32025.09 | 16.7 | 96.7 | |
| Llama-3.1-8B-Instruct2025.09 | 16.2 | 42.9 | |
| Time-MQABase LLM=Llama3-8B2025.09 | 11.6 | 15.8 | |
| ChatTS2025.09 | 11.1 | 27.1 | |
| Time-MQABase LLM=Mistral-7B-v0.32025.09 | 10 | 47.3 |