Information Extraction on Multiple Tasks 2
95.56DeathsGemini2.5-pro
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Gemini2.5-proModel category=Full-sized Large Model2025.12 | 95.56 | 89.32 | 92.45 | 78.23 | 77.53 | |
| Qwen2.5-7b-loraModel category=Small Model, Training method=LoRA Fine-tuning2025.12 | 95.31 | 92.55 | 89.78 | 95.54 | 85.73 | |
| Gpt-5Model category=Full-sized Large Model2025.12 | 94.25 | 88.62 | 87.54 | 79.24 | 72.15 | |
| Deepseek v3Model category=Full-sized Large Model2025.12 | 93.75 | 84.72 | 84.38 | 90.65 | 77.89 | |
| Claude-4Model category=Full-sized Large Model2025.12 | 93.2 | 86.45 | 91.43 | 76.34 | 73.23 | |
| Qwen-maxModel category=Full-sized Large Model2025.12 | 92.71 | 80.87 | 88.38 | 79.44 | 81.81 |