EVALITA - relation-extraction — leaderboard
Metric: CPS. Source: huggingface.co. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Large 2 (Nov) Instruct (2411) | 66.82 |
| 2 | Gemma 2 9B (IT) | 51.26 |
| 3 | Gemma 3n E4B (IT) | 49.65 |
| 4 | Gemma 3 27B (IT) | 48.48 |
| 5 | Qwen2.5-14B-Instruct-1M | 44.23 |
| 6 | LLaMAntino-3-ANITA-8B-Inst-DPO-ITA | 42.14 |
| 7 | Qwen 2.5 72B Instruct | 41.6 |
| 8 | Gemma 3 12B (IT) | 41.59 |
| 9 | Mistral Small 3 | 40.9 |
| 10 | granite-3.1-8B-instruct | 39.91 |
| 11 | Qwen 3 Next 80B A3B Instruct | 38.87 |
| 12 | Qwen 2.5 VL 32B Instruct | 38.41 |
| 13 | DeepSeek R1 Distill Llama 70B | 37.34 |
| 14 | Phi-4 | 37.15 |
| 15 | Phi-3-medium-4k-instruct | 36.95 |
Interactive version: theaggregate.ai/benchmark?slug=evalita-relation-extraction · How the rankings work · Data refreshed daily, snapshot 2026-07-22.