EVALITA - sentiment-analysis — leaderboard
Metric: CPS. Source: huggingface.co. 48 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Large 2 (Nov) Instruct (2411) | 80.94 |
| 2 | Gemma 3 27B (IT) | 80.3 |
| 3 | calme-3.2-instruct-78B | 80.15 |
| 4 | Llama 3.3 70B Instruct | 79.55 |
| 5 | Gemma 3 12B (IT) | 78.34 |
| 6 | Qwen 2.5 72B Instruct | 77.68 |
| 7 | DeepSeek R1 Distill Llama 70B | 77.48 |
| 8 | Gemma 3n E4B (IT) | 76.34 |
| 9 | Mistral Small 3 | 75.95 |
| 10 | Gemma 3 4B (IT) | 75.3 |
| 11 | Llama-3.1-SuperNova-Lite | 75.24 |
| 12 | Phi-4 | 75.21 |
| 13 | granite-3.1-8B-instruct | 74.76 |
| 14 | Gemma 2 27B (IT) | 74.26 |
| 15 | Qwen 2.5 7B Instruct | 74.16 |
Interactive version: theaggregate.ai/benchmark?slug=evalita-sentiment-analysis · How the rankings work · Data refreshed daily, snapshot 2026-07-22.