Scenario Understanding on Scenario Understanding (OOD)
100Success RateGPT-4.1-2025-04-14
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-4.1-2025-04-142025.09 | 100 | 87.8 | |
| Llama-3.1-70B-Instruct2025.09 | 100 | 59.6 | |
| Mistral-Small-3.1-24B-Ins2025.09 | 100 | 69.2 | |
| Qwen2.5-Instruct-7B2025.09 | 100 | 42.8 | |
| GPT-4.1-Nano2025.09 | 98.7 | 62.6 | |
| TIMEOMNI-1Base LLM=Qwen2.5-Instruct-7B2025.09 | 98.3 | 87.7 | |
| Time-R1Base LLM=Qwen2.5-Instruct-7B2025.09 | 92.5 | 34 | |
| Mistral-7B-v0.32025.09 | 87.6 | 34.7 | |
| Llama-3.1-8B-Instruct2025.09 | 46.8 | 32.1 | |
| Time-MQABase LLM=Llama3-8B2025.09 | 32.6 | 25.1 | |
| Time-MQABase LLM=Qwen2.5-7B2025.09 | 22.7 | 37.5 | |
| Time-MQABase LLM=Mistral-7B-v0.32025.09 | 22.1 | 27.8 | |
| ChatTS2025.09 | 6.9 | — |