Open Domain Event Detection on SEOE
75.35PrecisionClaude-3.5-haiku
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude-3.5-haikuSeries=Closed-source Claude Series LLMs2025.03 | 75.35 | 44.26 | 55.76 | |
| Llama-3.1-8B-ChatSeries=Open-source Llama-3 Series LLMs2025.03 | 74.77 | 42.73 | 54.38 | |
| GPT-4oSeries=Closed-source GPT Series LLMs2025.03 | 73.58 | 45.61 | 56.31 | |
| Llama-3.2-70B-ChatSeries=Open-source Llama-3 Series LLMs2025.03 | 72.28 | 45.77 | 56.05 | |
| InternLM-2.5-20BSeries=Open-source InternLM Series LLMs2025.03 | 72.08 | 43.84 | 54.52 | |
| InternLM-2.5-7BSeries=Open-source InternLM Series LLMs2025.03 | 71.64 | 42.88 | 53.65 | |
| Qwen-2.5-7B-ChatSeries=Open-source Qwen Series LLMs2025.03 | 71.16 | 43.43 | 53.94 | |
| GPT-3.5-turboSeries=Closed-source GPT Series LLMs2025.03 | 69.43 | 42.89 | 53.02 | |
| Qwen-2.5-72B-ChatSeries=Open-source Qwen Series LLMs2025.03 | 68.83 | 49.2 | 57.38 | |
| Claude-3.5-sonnetSeries=Closed-source Claude Series LLMs2025.03 | 68.47 | 48.2 | 56.57 | |
| GPT-4Series=Closed-source GPT Series LLMs2025.03 | 67.46 | 45.12 | 54.08 | |
| GPT-4-turboSeries=Closed-source GPT Series LLMs2025.03 | 66.53 | 45.23 | 53.85 | |
| Gemini-1.5-flashSeries=Closed-source Gemini Series LLMs2025.03 | 64.68 | 52.41 | 57.9 | |
| Gemini-1.5-proSeries=Closed-source Gemini Series LLMs2025.03 | 63.45 | 49.19 | 55.42 | |
| o1-previewSeries=Closed-source GPT Series LLMs2025.03 | 62.67 | 56.59 | 59.47 |